← All Mac Studio models

Mac Studio M5 Ultra

The M5 Ultra Mac Studio runs local models at 1228 GB/s of memory bandwidth with 96 to 512 GB of unified memory. On Apple Silicon that memory is shared with the GPU, so the whole pool is available for weights: at 512 GB you can hold roughly a 696B dense model at Q4. Two Max dies fused together: the widest memory bus and the highest capacity Apple sells. This is the tier that runs frontier-size open weights locally.

By , Founder & Lead Engineer— Updated

Specifications

ChipApple M5 Ultra
CPU cores30 or 36
GPU cores64 or 80
Unified memory96, 256, or 512 GB
Memory bandwidth1228 GB/s
Neural Engine76 TOPS
Released2026
AvailabilitySold new by Apple

Memory bandwidth is faster than 95% of the Apple Silicon chips shipped in a Mac, against a 1228 GB/s peak.

Its memory ceiling is above 90% of them, against a 512 GB peak.

Pick your configuration

Every option Apple sells with this chip. The model list below recomputes against the one you pick.

GPU cores

Unified memory

Apple couples memory to the core count on this chip, so the options change with the bin above.

What each memory option runs

Unified memory is the ceiling and it is soldered, so this is the decision you cannot revisit.

96 GB unified memory

84 GB usable for weights · 1228 GB/s

6,384 of 6,563 models fit, and 6,271 of them run with headroom rather than as a squeeze.

Largest model at Q4
LING 3.0 FLASH ABLITERATED · 127.49B
Best all-round pick
Ornith 1.0 35B · Q8_0 · ~236 tok/s

256 GB unified memory

225 GB usable for weights · 1228 GB/s

6,493 of 6,563 models fit, and 6,424 of them run with headroom rather than as a squeeze.

Largest model at Q4
DeepSeek V3.2 REAP 345B A37B · 344.89B
Best all-round pick
Ornith 1.0 35B · Q8_0 · ~236 tok/s

512 GB unified memory

450 GB usable for weights · 1228 GB/s

6,549 of 6,563 models fit, and 6,490 of them run with headroom rather than as a squeeze.

Largest model at Q4
A.X K2 · 691.69B
Best all-round pick
Ornith 1.0 35B · Q8_0 · ~236 tok/s

What a 96 GB M5 Ultra Mac Studio can run

Every model in the database against this exact configuration, at 1228 GB/s. Ratings and speeds are the same numbers the model pages show.

Showing 6563 of 6563 models

Ornith 1.0 35B

General · deepreinforce-ai · 2026-06-21

Q8_0Excellent
38.6 GB40% of RAMBenchmark needed34.13B params
Run with ToolPiper
Ornith 1.0 9B

General · deepreinforce-ai · 2026-06-21

Q8_0Excellent
9.7 GB10% of RAM~78 tok/sEstimated8.21B params
Run with ToolPiper
Kimi K3 DSpark

General · radixark · 2026-07-27

Q8_0Excellent
3.0 GB3% of RAM~286 tok/sEstimated2.25B params
Run with ToolPiper
Qwen3.6 35B A3B abliterated v4

General · bahushruth · 2026-06-11

Q8_0Excellent
39.2 GB41% of RAMBenchmark needed34.66B params
Run with ToolPiper
MiniCPM5 1B

General · openbmb · 2026-05-21

Q8_0Excellent
1.7 GB2% of RAM~596 tok/sEstimated1.08B params
Run with ToolPiper
OTel LLM 8B A1B IT

General · farbodtavakkoli · 2026-06-17

Q8_0Excellent
10.8 GB11% of RAMBenchmark needed9.23B params
Run with ToolPiper
Agents A1 4B

General · internscience · 2026-07-13

Q8_0Excellent
5.6 GB6% of RAM~142 tok/sEstimated4.54B params
Run with ToolPiper
LFM2.5 8B A1B

General · Liquid AI · 2026-05-28

Q8_0Excellent
9.9 GB10% of RAMBenchmark needed8.47B params
Run with ToolPiper
automotive

General · flywheel-ai · 2026-06-21

Q8_0Excellent
39.2 GB41% of RAMBenchmark needed34.66B params
Run with ToolPiper
VibeThinker 3B

General · weiboai · 2026-06-12

Q8_0Excellent
3.9 GB4% of RAM~208 tok/sEstimated3.09B params
Run with ToolPiper
LFM2.5 2.6B

General · Liquid AI · 2026-07-28

Q8_0Excellent
3.5 GB4% of RAM~238 tok/sEstimated2.7B params
Run with ToolPiper
Qwen AgentWorld 35B A3B

General · Alibaba · 2026-06-22

Q8_0Excellent
39.2 GB41% of RAMBenchmark needed34.66B params
Run with ToolPiper
Laguna XS 2.1

General · poolside · 2026-06-20

Q8_0Excellent
37.8 GB39% of RAMBenchmark needed33.44B params
Run with ToolPiper
LFM2.5 230M

General · Liquid AI · 2026-06-24

Q8_0Excellent
0.8 GB1% of RAM~2,797 tok/sEstimated0.23B params
Run with ToolPiper
Nanbeige4.2 3B

General · nanbeige · 2026-07-21

Q8_0Excellent
5.2 GB5% of RAM~154 tok/sEstimated4.17B params
Run with ToolPiper
Qwythos 9B Claude Mythos 5 1M

General · empero-ai · 2026-06-19

Q8_0Excellent
11.0 GB11% of RAM~68 tok/sEstimated9.41B params
Run with ToolPiper
Qwen3.8_4B_Distilled_GGUF

General · ma7ee7 · 2026-07-30

Q8_0Excellent
4.0 GB4% of RAM~206 tok/sEstimated3.13B params
Run with ToolPiper
Apodex 1.0 mini

General · apodex · 2026-06-07

Q8_0Excellent
40.6 GB42% of RAMBenchmark needed35.95B params
Run with ToolPiper
Agents A1

General · internscience · 2026-06-22

Q8_0Excellent
39.7 GB41% of RAMBenchmark needed35.11B params
Run with ToolPiper
North Mini Code 1.0

Coding · coherelabs · 2026-06-05

Q8_0Excellent
34.5 GB36% of RAMBenchmark needed30.48B params
Run with ToolPiper
JOSIE 2 2B OSS

General · goekdeniz-guelmez · 2026-07-31

Q8_0Excellent
3.0 GB3% of RAM~283 tok/sEstimated2.27B params
Run with ToolPiper
JOSIE 2 9B OSS

General · goekdeniz-guelmez · 2026-07-31

Q8_0Excellent
11.3 GB12% of RAM~67 tok/sEstimated9.65B params
Run with ToolPiper
minicpm5 1b hermes toolhv1

General · ktruestory · 2026-05-28

Q8_0Excellent
1.7 GB2% of RAM~596 tok/sEstimated1.08B params
Run with ToolPiper
FrankenCPM 4x1B A2B

General · petrouil · 2026-07-23

Q8_0Excellent
3.4 GB4% of RAMBenchmark needed2.61B params
Run with ToolPiper
Qwen3.6 35B A3B

Multimodal · Alibaba · 2026-04-15

Q8_0Excellent
40.6 GB42% of RAMBenchmark needed35.95B params
Run with ToolPiper
granite 4.1 8b

General · ibm-granite · 2026-04-06

Q8_0Excellent
10.3 GB11% of RAM~73 tok/sEstimated8.79B params
Run with ToolPiper
gemma 4 12b it

Multimodal · google · 2026-05

Q8_0Excellent
13.8 GB14% of RAM~54 tok/sEstimated11.96B params
Run with ToolPiper
granite 4.1 3b

General · ibm-granite · 2026-04-06

Q8_0Excellent
4.3 GB4% of RAM~189 tok/sEstimated3.4B params
Run with ToolPiper
gemma 4 12B agentic fable5 composer2.5 v2 3.5x tau2

General · yuxinlu1 · 2026-06-28

Q8_0Excellent
13.8 GB14% of RAM~54 tok/sEstimated11.96B params
Run with ToolPiper
granite vision 4.1 4b

Multimodal · ibm-granite · 2026-04-16

Q8_0Excellent
5.0 GB5% of RAM~161 tok/sEstimated4B params
Run with ToolPiper
LFM2.5 350M

General · Liquid AI · 2026-03-31

Q8_0Excellent
0.9 GB1% of RAM~1,838 tok/sEstimated0.35B params
Run with ToolPiper
granite guardian 4.1 8b

General · ibm-granite · 2026-04-16

Q8_0Excellent
9.8 GB10% of RAM~77 tok/sEstimated8.38B params
Run with ToolPiper
dspv2_guide

General · lukebailey181pub · 2026-04-21

Q8_0Excellent
8.2 GB9% of RAM~93 tok/sEstimated6.91B params
Run with ToolPiper
gemma 4 26B A4B it uncensored

General · trevorjs · 2026-04-03

Q8_0Excellent
29.3 GB31% of RAMBenchmark needed25.81B params
Run with ToolPiper
Laguna XS.2

General · poolside · 2026-04-23

Q8_0Excellent
37.8 GB39% of RAMBenchmark needed33.44B params
Run with ToolPiper
Gemma 4 12B OBLITERATED

General · obliteratus · 2026-06-05

Q8_0Excellent
13.8 GB14% of RAM~54 tok/sEstimated11.96B params
Run with ToolPiper
Huihui gemma 4 12B agentic fable5 abliterated

General · huihui-ai · 2026-07-11

Q8_0Excellent
13.8 GB14% of RAM~54 tok/sEstimated11.96B params
Run with ToolPiper
gemma 4 E4B it OBLITERATED

General · obliteratus · 2026-04-15

Q8_0Excellent
9.4 GB10% of RAM~80 tok/sEstimated8B params
Run with ToolPiper
Huihui Qwen3.6 35B A3B Claude 4.7 Opus abliterated

General · huihui-ai · 2026-04-21

Q8_0Excellent
40.6 GB42% of RAMBenchmark needed35.95B params
Run with ToolPiper
Huihui Qwen3.6 35B A3B abliterated

Multimodal · huihui-ai · 2026-04-18

Q8_0Excellent
40.6 GB42% of RAMBenchmark needed35.95B params
Run with ToolPiper
Qwen3.5 9B

Multimodal · Alibaba · 2026-02-27

Q8_0Excellent
11.3 GB12% of RAM~67 tok/sEstimated9.65B params
Run with ToolPiper
gemma 4 26B A4B it

Multimodal · Google · 2026-03-11

Q8_0Excellent
30.1 GB31% of RAMBenchmark needed26.54B params
Run with ToolPiper
Qwen3.5 4B

Multimodal · Alibaba · 2026-02-27

Q8_0Excellent
5.7 GB6% of RAM~138 tok/sEstimated4.66B params
Run with ToolPiper
gemma 4 E4B it

Multimodal · Google · 2026-03-02

Q8_0Excellent
9.4 GB10% of RAM~80 tok/sEstimated8B params
Run with ToolPiper
gemma 4 E2B it

Multimodal · Google · 2026-03-02

Q8_0Excellent
6.2 GB6% of RAM~126 tok/sEstimated5.12B params
Run with ToolPiper
Qwen3.5 0.8B

Multimodal · Alibaba · 2026-02-28

Q8_0Excellent
1.5 GB2% of RAM~739 tok/sEstimated0.87B params
Run with ToolPiper
Qwen3.5 2B

Multimodal · Alibaba · 2026-02-28

Q8_0Excellent
3.0 GB3% of RAM~283 tok/sEstimated2.27B params
Run with ToolPiper
Qwen3.5 35B A3B

Multimodal · Alibaba · 2026-02-24

Q8_0Excellent
40.6 GB42% of RAMBenchmark needed35.95B params
Run with ToolPiper
Qwen3.5 0.8B Base

Multimodal · Alibaba · 2026-02-28

Q8_0Excellent
1.5 GB2% of RAM~739 tok/sEstimated0.87B params
Run with ToolPiper
Qwen3.5 2B Base

Multimodal · Alibaba · 2026-02-28

Q8_0Excellent
3.0 GB3% of RAM~283 tok/sEstimated2.27B params
Run with ToolPiper
Qwen3.5 9B Base

Multimodal · Alibaba · 2026-02-26

Q8_0Excellent
11.3 GB12% of RAM~67 tok/sEstimated9.65B params
Run with ToolPiper
Qwen3.5 4B Base

Multimodal · Alibaba · 2026-02-27

Q8_0Excellent
5.7 GB6% of RAM~138 tok/sEstimated4.66B params
Run with ToolPiper
Nemotron Labs Diffusion 8B

General · nvidia · 2026-03-18

Q8_0Excellent
10.0 GB10% of RAM~76 tok/sEstimated8.49B params
Run with ToolPiper
Dolphin3 Cyber 8B

General · ravichandranj · 2026-02-13

Q8_0Excellent
7.7 GB8% of RAM~100 tok/sEstimated6.43B params
Run with ToolPiper
Nemotron Cascade 2 30B A3B

General · nvidia · 2026-03-18

Q8_0Excellent
35.7 GB37% of RAMBenchmark needed31.58B params
Run with ToolPiper
sarvam 30b

General · sarvamai · 2026-03-03

Q8_0Excellent
36.4 GB38% of RAMBenchmark needed32.15B params
Run with ToolPiper
Nemotron Labs Diffusion 3B

General · nvidia · 2026-03-02

Q8_0Excellent
4.8 GB5% of RAM~168 tok/sEstimated3.83B params
Run with ToolPiper
LFM2 24B A2B

General · Liquid AI · 2026-02-24

Q8_0Excellent
27.1 GB28% of RAMBenchmark needed23.84B params
Run with ToolPiper
Qwen3.5 9B Claude 4.6 Opus Reasoning Distilled v2

Reasoning · jackrong · 2026-03-16

Q8_0Excellent
11.3 GB12% of RAM~67 tok/sEstimated9.65B params
Run with ToolPiper
Qwen3.5 35B A3B Claude 4.6 Opus Reasoning Distilled

Reasoning · jackrong · 2026-03-07

Q8_0Excellent
40.6 GB42% of RAMBenchmark needed35.95B params
Run with ToolPiper
pii guard turkish 270m

General · cagrigungor · 2026-08-06

Q8_0Excellent
0.8 GB1% of RAM~2,382 tok/sEstimated0.27B params
Run with ToolPiper
GLM 4.7 Flash

General · zai-org · 2026-01-19

Q8_0Excellent
35.3 GB37% of RAMBenchmark needed31.22B params
Run with ToolPiper
LFM2.5 VL 1.6B

Multimodal · Liquid AI · 2026-01-05

Q8_0Excellent
2.3 GB2% of RAM~402 tok/sEstimated1.6B params
Run with ToolPiper
LFM2.5 1.2B Thinking

General · Liquid AI · 2026-01-20

Q8_0Excellent
1.8 GB2% of RAM~550 tok/sEstimated1.17B params
Run with ToolPiper
gemma 3 12b it heretic

General · dreamfast · 2026-01-11

Q8_0Excellent
14.1 GB15% of RAM~53 tok/sEstimated12.19B params
Run with ToolPiper
AI21 Jamba2 3B

General · ai21labs · 2026-01-06

Q8_0Excellent
3.9 GB4% of RAMBenchmark needed3.03B params
Run with ToolPiper
Llama 3.1 8B Instruct pearl

Chat · pearl-ai · 2026-02-26

Q8_0Excellent
9.5 GB10% of RAM~80 tok/sEstimated8.03B params
Run with ToolPiper
OneReason 0.8B pretrain competition

Reasoning · openonerec · 2026-06-09

Q8_0Excellent
1.4 GB1% of RAM~804 tok/sEstimated0.8B params
Run with ToolPiper
LFM2.5 1.2B Base

General · Liquid AI · 2026-01-05

Q8_0Excellent
1.8 GB2% of RAM~550 tok/sEstimated1.17B params
Run with ToolPiper
LFM2.5 1.2B JP

General · Liquid AI · 2026-01-04

Q8_0Excellent
1.8 GB2% of RAM~550 tok/sEstimated1.17B params
Run with ToolPiper
LFM2 2.6B Exp

General · Liquid AI · 2025-12-25

Q8_0Excellent
3.4 GB4% of RAM~250 tok/sEstimated2.57B params
Run with ToolPiper
LFM2 2.6B Transcript

General · Liquid AI · 2026-01-05

Q8_0Excellent
3.4 GB4% of RAM~250 tok/sEstimated2.57B params
Run with ToolPiper
Gemma 3 4B VL it Gemini Pro Heretic Uncensored Thinking

Multimodal · davidau · 2026-02-02

Q8_0Excellent
5.3 GB6% of RAM~150 tok/sEstimated4.3B params
Run with ToolPiper
LaSER Qwen3 8B

General · alibaba-nlp · 2026-03-31

Q8_0Excellent
9.6 GB10% of RAM~79 tok/sEstimated8.19B params
Run with ToolPiper
LFM2.5 1.2B Instruct

Chat · Liquid AI · 2026-01-06

Q8_0Excellent
1.8 GB2% of RAM~550 tok/sEstimated1.17B params
Run with ToolPiper
lynx instruct 30b

Chat · bineric · 2026-01-12

Q8_0Excellent
34.6 GB36% of RAMBenchmark needed30.53B params
Run with ToolPiper
LLaDA2.1 mini

General · inclusionai · 2026-02-09

Q8_0Excellent
18.6 GB19% of RAMBenchmark needed16.26B params
Run with ToolPiper
TimeOmni 1 7B

General · anton-hugging · 2026-02-06

Q8_0Excellent
9.0 GB9% of RAM~84 tok/sEstimated7.62B params
Run with ToolPiper
LFM2 ColBERT 350M

General · Liquid AI · 2025-10-28

Q8_0Excellent
0.9 GB1% of RAM~1,838 tok/sEstimated0.35B params
Run with ToolPiper
Olmo 3 7B Think

General · allenai · 2025-11-18

Q8_0Excellent
8.6 GB9% of RAM~88 tok/sEstimated7.3B params
Run with ToolPiper
LFM2 8B A1B

General · Liquid AI · 2025-10-07

Q8_0Excellent
9.8 GB10% of RAMBenchmark needed8.34B params
Run with ToolPiper
Olmo Hybrid 7B

General · allenai · 2026-01-28

Q8_0Excellent
8.8 GB9% of RAM~87 tok/sEstimated7.43B params
Run with ToolPiper
LFM2 VL 3B

Multimodal · Liquid AI · 2025-10-22

Q8_0Excellent
3.8 GB4% of RAM~214 tok/sEstimated3B params
Run with ToolPiper
Lumma 0.6B Extract

General · frontiersmind · 2026-08-03

Q8_0Excellent
1.2 GB1% of RAM~990 tok/sEstimated0.65B params
Run with ToolPiper
gpt oss 20b

General · openai · 2025-08-04

Q8_0Excellent
24.5 GB26% of RAMBenchmark needed21.51B params
Run with ToolPiper
Qwen3 Coder 30B A3B Instruct

Coding · Alibaba · 2025-07-31

Q8_0Excellent
34.6 GB36% of RAMBenchmark needed30.53B params
Run with ToolPiper
typhoon2.5 qwen3 4b

General · typhoon-ai · 2025-09-23

Q8_0Excellent
5.0 GB5% of RAM~160 tok/sEstimated4.02B params
Run with ToolPiper
T lite it 2.1

General · t-tech · 2025-12-22

Q8_0Excellent
9.6 GB10% of RAM~79 tok/sEstimated8.19B params
Run with ToolPiper
Qwen3 4B Thinking 2507

General · Alibaba · 2025-08-05

Q8_0Excellent
5.0 GB5% of RAM~160 tok/sEstimated4.02B params
Run with ToolPiper
Ilama 3.2 1B

General · hmellor · 2025-07-22

Q8_0Excellent
1.9 GB2% of RAM~519 tok/sEstimated1.24B params
Run with ToolPiper
NVIDIA Nemotron Nano 9B v2

General · nvidia · 2025-08-12

Q8_0Excellent
10.4 GB11% of RAM~72 tok/sEstimated8.89B params
Run with ToolPiper
granite 4.0 h tiny

General · ibm-granite · 2025-09-16

Q8_0Excellent
8.2 GB9% of RAMBenchmark needed6.94B params
Run with ToolPiper
droplychee 1.0 27b

Multimodal · droplychee · 2026-07-17

Q8_0Excellent
31.5 GB33% of RAM~23 tok/sEstimated27.78B params
Run with ToolPiper
granite 4.0 micro

General · ibm-granite · 2025-09-16

Q8_0Excellent
4.3 GB4% of RAM~189 tok/sEstimated3.4B params
Run with ToolPiper
LFM2 VL 450M

Multimodal · Liquid AI · 2025-08-12

Q8_0Excellent
1.0 GB1% of RAM~1,429 tok/sEstimated0.45B params
Run with ToolPiper
Olmo 3 1025 7B

General · allenai · 2025-09-12

Q8_0Excellent
8.6 GB9% of RAM~88 tok/sEstimated7.3B params
Run with ToolPiper
gpt oss safeguard 20b

General · openai · 2025-09-18

Q8_0Excellent
24.5 GB26% of RAMBenchmark needed21.51B params
Run with ToolPiper
Qwen3.8 27B

Multimodal · Alibaba · 2026-08-05

Q8_0Excellent
31.5 GB33% of RAM~23 tok/sEstimated27.78B params
Run with ToolPiper
Qwen3 8B DFlash b16

General · z-lab · 2026-01-04

Q8_0Excellent
9.4 GB10% of RAM~80 tok/sEstimated8B params
Run with ToolPiper
Qwen3 30B A3B Thinking 2507

General · Alibaba · 2025-07-29

Q8_0Excellent
34.6 GB36% of RAMBenchmark needed30.53B params
Run with ToolPiper
granite 4.0 h small

General · ibm-granite · 2025-09-16

Q8_0Excellent
36.4 GB38% of RAMBenchmark needed32.21B params
Run with ToolPiper
Qwen3.5 27B Claude 4.6 Opus Reasoning Distilled

Reasoning · jackrong · 2026-02-27

Q8_0Excellent
31.5 GB33% of RAM~23 tok/sEstimated27.78B params
Run with ToolPiper
XCurOS0.1 8B Instruct

Chat · xcuros · 2026-02-28

Q8_0Excellent
9.0 GB9% of RAM~84 tok/sEstimated7.62B params
Run with ToolPiper
OneRec 1.7B

General · openonerec · 2025-12-30

Q8_0Excellent
2.9 GB3% of RAM~302 tok/sEstimated2.13B params
Run with ToolPiper
granite 4.0 h micro

General · ibm-granite · 2025-09-16

Q8_0Excellent
4.1 GB4% of RAM~202 tok/sEstimated3.19B params
Run with ToolPiper
Ouro 1.4B

General · bytedance · 2025-10-28

Q8_0Excellent
2.1 GB2% of RAM~450 tok/sEstimated1.43B params
Run with ToolPiper
Qwen3 4B DFlash b16

General · z-lab · 2026-01-04

Q8_0Excellent
5.0 GB5% of RAM~161 tok/sEstimated4B params
Run with ToolPiper
LFM2 VL 1.6B

Multimodal · Liquid AI · 2025-08-12

Q8_0Excellent
2.3 GB2% of RAM~407 tok/sEstimated1.58B params
Run with ToolPiper
LFM2 2.6B

General · Liquid AI · 2025-09-22

Q8_0Excellent
3.4 GB4% of RAM~250 tok/sEstimated2.57B params
Run with ToolPiper
LFM2 350M PII Extract JP

General · Liquid AI · 2025-09-30

Q8_0Excellent
0.9 GB1% of RAM~1,838 tok/sEstimated0.35B params
Run with ToolPiper
LFM2 1.2B Extract

General · Liquid AI · 2025-08-22

Q8_0Excellent
1.8 GB2% of RAM~550 tok/sEstimated1.17B params
Run with ToolPiper
LFM2 350M ENJP MT

General · Liquid AI · 2025-09-03

Q8_0Excellent
0.9 GB1% of RAM~1,838 tok/sEstimated0.35B params
Run with ToolPiper
LFM2 1.2B RAG

General · Liquid AI · 2025-09-03

Q8_0Excellent
1.8 GB2% of RAM~550 tok/sEstimated1.17B params
Run with ToolPiper
LFM2 350M Math

General · Liquid AI · 2025-08-25

Q8_0Excellent
0.9 GB1% of RAM~1,838 tok/sEstimated0.35B params
Run with ToolPiper
LFM2 350M Extract

General · Liquid AI · 2025-09-03

Q8_0Excellent
0.9 GB1% of RAM~1,838 tok/sEstimated0.35B params
Run with ToolPiper
LFM2 1.2B Tool

General · Liquid AI · 2025-09-03

Q8_0Excellent
1.8 GB2% of RAM~550 tok/sEstimated1.17B params
Run with ToolPiper
VAETKI 20B A2B

General · NCAI · 2025-12-29

Q8_0Excellent
22.4 GB23% of RAMBenchmark needed19.6B params
Run with ToolPiper
VAETKI 7B A1B

General · NCAI · 2025-12-29

Q8_0Excellent
8.6 GB9% of RAMBenchmark needed7.25B params
Run with ToolPiper
Qwen3.6 27B

Multimodal · Alibaba · 2026-04-21

Q8_0Excellent
31.5 GB33% of RAM~23 tok/sEstimated27.78B params
Run with ToolPiper
DeepSeek R1 0528 Qwen3 8B

Reasoning · DeepSeek · 2025-05-29

Q8_0Excellent
9.6 GB10% of RAM~79 tok/sEstimated8.19B params
Run with ToolPiper
Olmo 3 7B Instruct

Chat · allenai · 2025-11-19

Q8_0Excellent
8.6 GB9% of RAM~88 tok/sEstimated7.3B params
Run with ToolPiper
Olmo 3 7B Instruct SFT

Chat · allenai · 2025-11-17

Q8_0Excellent
8.6 GB9% of RAM~88 tok/sEstimated7.3B params
Run with ToolPiper
NVIDIA Nemotron Nano 12B v2

General · nvidia · 2025-08-21

Q8_0Excellent
13.9 GB14% of RAM~54 tok/sEstimated12B params
Run with ToolPiper
avibe

General · avitotech · 2025-10-20

Q8_0Excellent
9.3 GB10% of RAM~81 tok/sEstimated7.9B params
Run with ToolPiper
LLaDA2.0 mini

General · inclusionai · 2025-11-25

Q8_0Excellent
18.6 GB19% of RAMBenchmark needed16.26B params
Run with ToolPiper
granite 4.0 tiny preview

General · ibm-granite · 2025-04-30

Q8_0Excellent
7.9 GB8% of RAMBenchmark needed6.67B params
Run with ToolPiper
LFM2 1.2B

General · Liquid AI · 2025-07-10

Q8_0Excellent
1.8 GB2% of RAM~550 tok/sEstimated1.17B params
Run with ToolPiper
Phi 4 mini reasoning

Reasoning · Microsoft · 2025-04-29

Q8_0Excellent
4.8 GB5% of RAM~168 tok/sEstimated3.84B params
Run with ToolPiper
MiniCPM4.1 8B

General · openbmb · 2025-09-02

Q8_0Excellent
9.6 GB10% of RAM~79 tok/sEstimated8.19B params
Run with ToolPiper
PARD Llama 3.2 1B

General · amd · 2025-05-17

Q8_0Excellent
2.2 GB2% of RAM~429 tok/sEstimated1.5B params
Run with ToolPiper
newsvibe categories multilingual llama 1b

General · stefanruseti · 2025-06-04

Q8_0Excellent
1.9 GB2% of RAM~519 tok/sEstimated1.24B params
Run with ToolPiper
granite 4.0 350m base

General · ibm-granite · 2025-10-07

Q8_0Excellent
0.9 GB1% of RAM~1,838 tok/sEstimated0.35B params
Run with ToolPiper
EuroLLM 9B Instruct 2512

Chat · utter-project · 2026-01-26

Q8_0Excellent
10.7 GB11% of RAM~70 tok/sEstimated9.15B params
Run with ToolPiper
EXAONE 4.0 1.2B

General · lgai-exaone · 2025-07-11

Q8_0Excellent
1.9 GB2% of RAM~503 tok/sEstimated1.28B params
Run with ToolPiper
LFM2 350M

General · Liquid AI · 2025-07-10

Q8_0Excellent
0.9 GB1% of RAM~1,838 tok/sEstimated0.35B params
Run with ToolPiper
Jan nano 128k

General · menlo · 2025-06-25

Q8_0Excellent
5.0 GB5% of RAM~160 tok/sEstimated4.02B params
Run with ToolPiper
LFM2 700M

General · Liquid AI · 2025-07-10

Q8_0Excellent
1.3 GB1% of RAM~869 tok/sEstimated0.74B params
Run with ToolPiper
gemma 3 12b it abliterated v2

Multimodal · mlabonne · 2025-05-28

Q8_0Excellent
13.6 GB14% of RAM~55 tok/sEstimated11.77B params
Run with ToolPiper
VAETKI VL 7B A1B

Multimodal · NCAI · 2025-12-29

Q8_0Excellent
9.0 GB9% of RAMBenchmark needed7.58B params
Run with ToolPiper
Qwen2.5 VL 7B Instruct

Multimodal · Alibaba · 2025-01-26

Q8_0Excellent
9.7 GB10% of RAM~78 tok/sEstimated8.29B params
Run with ToolPiper
Qwen2.5 VL 3B Instruct

Multimodal · Alibaba · 2025-01-26

Q8_0Excellent
4.7 GB5% of RAM~172 tok/sEstimated3.75B params
Run with ToolPiper
Qwen3.5 27B

Multimodal · Alibaba · 2026-02-24

Q8_0Excellent
31.5 GB33% of RAM~23 tok/sEstimated27.78B params
Run with ToolPiper
SmolLM3 3B

General · huggingfacetb · 2025-07-08

Q8_0Excellent
3.9 GB4% of RAM~209 tok/sEstimated3.08B params
Run with ToolPiper
DeepSeek R1 Distill Qwen 1.5B

Reasoning · DeepSeek · 2025-01-20

Q8_0Excellent
2.5 GB3% of RAM~361 tok/sEstimated1.78B params
Run with ToolPiper
Qwen3Guard Gen 4B

General · Alibaba · 2025-09-23

Q8_0Excellent
5.4 GB6% of RAM~146 tok/sEstimated4.41B params
Run with ToolPiper
DeepSeek R1 Distill Llama 8B

Reasoning · DeepSeek · 2025-01-20

Q8_0Excellent
9.5 GB10% of RAM~80 tok/sEstimated8.03B params
Run with ToolPiper
DeepSeek R1 Distill Qwen 7B

Reasoning · DeepSeek · 2025-01-20

Q8_0Excellent
9.0 GB9% of RAM~84 tok/sEstimated7.62B params
Run with ToolPiper
gemma4 e4b claims comparison

General · k-chirkunov · 2026-07-14

Q8_0Excellent
9.4 GB10% of RAM~81 tok/sEstimated7.94B params
Run with ToolPiper
SmolLM3 3B Base

General · huggingfacetb · 2025-06-19

Q8_0Excellent
3.9 GB4% of RAM~209 tok/sEstimated3.08B params
Run with ToolPiper
Qwen3Guard Gen 0.6B

General · Alibaba · 2025-09-23

Q8_0Excellent
1.3 GB1% of RAM~858 tok/sEstimated0.75B params
Run with ToolPiper

64-core vs 80-core GPU

Both bins run the same 1228 GB/s memory bus, so token generation is the same on either one. The extra cores show up in image and video work, not in tokens per second.

ConfigurationMemory bandwidthMemory optionsModels that fit
30-core CPU, 64-core GPU1228 GB/s96 GBIdentical
36-core CPU, 80-core GPU1228 GB/s256, 512 GBIdentical

Measured on the M5 Ultra

Nobody has submitted a benchmark on the M5 Ultra yet, so every speed on this page is the formula estimate rather than a measured run. The estimate is bandwidth-driven and calibrated against chips that do have data, which makes it a good guide and not a promise.

ToolPiper contributes a result anonymously when you run the benchmark, and the leaderboard shows every chip that already has one.

Where to go from here

What each step actually changes for local models, rather than which one is newer.

Used market alternative

Mac Studio M3 Ultra

33% less memory bandwidth

Why unified memory is the number that matters

On a PC the model has to fit in GPU VRAM, which is a separate pool from system RAM and usually the smaller of the two. Apple Silicon has one pool. The M5 Ultra's 1228 GB/s bus is shared by CPU, GPU, and Neural Engine, so a 512 GB machine can hand almost all of that to a model with no copy across a bus.

The Studio exists for this workload. It carries the widest memory buses and the highest capacities Apple sells, and it runs at full clocks indefinitely. Buy the memory, not the cores: every extra GB raises what you can load, while the core count only moves throughput on models that already fit.

Common questions

Can the M5 Ultra Mac Studio run a 70B model?

Yes, at 512 GB. A 70B model at Q4_K_M needs about 46 GB including an 8K context, and 512 GB of unified memory leaves about 450 GB for weights once macOS takes its share. At 96 GB it does not fit at any quantization worth running.

How much unified memory should I get with the M5 Ultra Mac Studio?

Memory is the only spec that changes what you can run at all. 96 GB holds about a 129B model at Q4; 512 GB holds about 696B. It is soldered, so this is a one-time decision, and it is the upgrade worth paying for before core count.

How fast are local LLMs on the M5 Ultra?

Token generation is bandwidth-bound, so M5 Ultra throughput scales with its 1228 GB/s memory bus. Divide bandwidth by the size of the weights actually read per token to get the ceiling, then expect roughly half of that in practice. A 7B model at Q4 reads about 4 GB per token pass, so the M5 Ultra lands in the tens of tokens per second and a 70B model lands in the single digits.

Is the 80-core GPU worth it over the 64-core on the M5 Ultra?

Not for LLMs. Both bins run the same 1228 GB/s memory bus and take the same memory options, and token generation is bound by bandwidth rather than GPU cores. The extra cores show up in image generation and video work, not in tokens per second.

Should I buy the M5 Ultra Mac Studio now or wait for the next one?

Buy on the memory you need today. Apple raises memory ceilings slowly and bandwidth in steps, and the M5 Ultra already holds about a 696B model at Q4. If your target model fits in 512 GB, waiting buys throughput rather than capability.

Run these models on your Mac Studio

ToolPiper downloads, manages, and runs local models on Apple Silicon. Free, and nothing leaves the machine.

Get ToolPiperCompare against another Mac