What LLMs Can Run on Your Mac?

Chip

Unified Memory

Bandwidth 307 GB/s

Available for Models ~21 GB

Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro

Model Compatibility

Showing 3641 of 3641 models

Multimodal · Alibaba · 2026-02-28

Q8_0Excellent

1.5 GB6% of RAM~185 tok/sEstimated0.87B params

Run with ToolPiper

Multimodal · Alibaba · 2026-02-28

Q8_0Excellent

3.0 GB13% of RAM~71 tok/sEstimated2.27B params

Run with ToolPiper

Qwen3.5 0.8B Base

Multimodal · Alibaba · 2026-02-28

Q8_0Excellent

1.5 GB6% of RAM~185 tok/sEstimated0.87B params

Run with ToolPiper

Qwen3.5 2B Base

Multimodal · Alibaba · 2026-02-28

Q8_0Excellent

3.0 GB13% of RAM~71 tok/sEstimated2.27B params

Run with ToolPiper

Multimodal · Alibaba · 2026-02-27

Q8_0Excellent

5.7 GB24% of RAM~35 tok/sEstimated4.66B params

Run with ToolPiper

Qwen3.5 4B Base

Multimodal · Alibaba · 2026-02-27

Q8_0Excellent

5.7 GB24% of RAM~35 tok/sEstimated4.66B params

Run with ToolPiper

General · Liquid AI · 2025-11-28

Q8_0Excellent

1.8 GB8% of RAM~137 tok/sEstimated1.17B params

Run with ToolPiper

LFM2 ColBERT 350M

General · Liquid AI · 2025-11-28

Q8_0Excellent

0.9 GB4% of RAM~459 tok/sEstimated0.35B params

Run with ToolPiper

LFM2.5 1.2B Thinking

Reasoning · Liquid AI · 2025-11-28

Q8_0Excellent

1.8 GB8% of RAM~137 tok/sEstimated1.17B params

Run with ToolPiper

General · Liquid AI · 2025-11-28

Q8_0Excellent

9.8 GB41% of RAMBenchmark needed8.3B params

Run with ToolPiper

LFM2.5 1.2B Base

General · Liquid AI · 2025-11-28

Q8_0Excellent

1.8 GB8% of RAM~137 tok/sEstimated1.17B params

Run with ToolPiper

General · Liquid AI · 2025-11-28

Q8_0Excellent

0.9 GB4% of RAM~459 tok/sEstimated0.35B params

Run with ToolPiper

General · Liquid AI · 2025-11-28

Q8_0Excellent

3.4 GB14% of RAM~63 tok/sEstimated2.57B params

Run with ToolPiper

General · Liquid AI · 2025-11-28

Q8_0Excellent

1.3 GB6% of RAM~217 tok/sEstimated0.74B params

Run with ToolPiper

LFM2 1.2B Extract

General · Liquid AI · 2025-11-28

Q8_0Excellent

1.8 GB8% of RAM~137 tok/sEstimated1.17B params

Run with ToolPiper

LFM2 350M Extract

General · Liquid AI · 2025-11-28

Q8_0Excellent

0.9 GB4% of RAM~459 tok/sEstimated0.35B params

Run with ToolPiper

LFM2 2.6B Transcript

General · Liquid AI · 2025-11-28

Q8_0Excellent

3.4 GB14% of RAM~63 tok/sEstimated2.57B params

Run with ToolPiper

LFM2 350M PII Extract JP

General · Liquid AI · 2025-11-28

Q8_0Excellent

0.9 GB4% of RAM~459 tok/sEstimated0.35B params

Run with ToolPiper

General · Liquid AI · 2025-11-28

Q8_0Excellent

1.8 GB8% of RAM~137 tok/sEstimated1.17B params

Run with ToolPiper

LFM2 350M ENJP MT

General · Liquid AI · 2025-11-28

Q8_0Excellent

0.9 GB4% of RAM~459 tok/sEstimated0.35B params

Run with ToolPiper

General · Liquid AI · 2025-11-28

Q8_0Excellent

1.8 GB8% of RAM~137 tok/sEstimated1.17B params

Run with ToolPiper

Reasoning · Liquid AI · 2025-11-28

Q8_0Excellent

0.9 GB4% of RAM~459 tok/sEstimated0.35B params

Run with ToolPiper

granite 4.0 h tiny

General · ibm-granite · 2025-09-16

Q8_0Excellent

8.2 GB34% of RAMBenchmark needed6.94B params

Run with ToolPiper

LFM2.5 1.2B Instruct

Chat · Liquid AI · 2025-11-28

Q8_0Excellent

1.8 GB8% of RAM~137 tok/sEstimated1.17B params

Run with ToolPiper

Chat · Liquid AI · 2025-11-28

Q8_0Excellent

3.4 GB14% of RAM~63 tok/sEstimated2.57B params

Run with ToolPiper

Chat · Liquid AI · 2025-11-28

Q8_0Excellent

1.8 GB8% of RAM~137 tok/sEstimated1.17B params

Run with ToolPiper

General · NCAI · 2025-12-29

Q8_0Excellent

8.6 GB36% of RAMBenchmark needed7.25B params

Run with ToolPiper

Reasoning · HuggingFace · 2025-07-08

Q8_0Excellent

3.8 GB16% of RAM~54 tok/sEstimated3B params

Run with ToolPiper

granite 4.0 h micro

General · ibm-granite · 2025-09-16

Q8_0Excellent

4.1 GB17% of RAM~50 tok/sEstimated3.19B params

Run with ToolPiper

LFM2.5 Audio 1.5B

General · Liquid AI · 2025-11-28

Q8_0Excellent

2.2 GB9% of RAM~107 tok/sEstimated1.5B params

Run with ToolPiper

LFM2 Audio 1.5B

General · Liquid AI · 2025-11-28

Q8_0Excellent

2.2 GB9% of RAM~107 tok/sEstimated1.5B params

Run with ToolPiper

VAETKI VL 7B A1B

Multimodal · NCAI · 2025-12-29

Q8_0Excellent

9.0 GB37% of RAMBenchmark needed7.58B params

Run with ToolPiper

Multimodal · Google · 2025-07-30

Q8_0Excellent

6.2 GB26% of RAM~32 tok/sEstimated5.1B params

Run with ToolPiper

gemma 3n E2B it

Multimodal · Google · 2025-06-25

Q8_0Excellent

5.0 GB21% of RAM~40 tok/sEstimated4B params

Run with ToolPiper

Multimodal · Liquid AI · 2025-11-28

Q8_0Excellent

1.0 GB4% of RAM~357 tok/sEstimated0.45B params

Run with ToolPiper

Multimodal · Liquid AI · 2025-11-28

Q8_0Excellent

2.3 GB10% of RAM~101 tok/sEstimated1.6B params

Run with ToolPiper

Multimodal · Liquid AI · 2025-11-28

Q8_0Excellent

3.8 GB16% of RAM~54 tok/sEstimated3B params

Run with ToolPiper

Multimodal · Liquid AI · 2025-11-28

Q8_0Excellent

2.3 GB9% of RAM~102 tok/sEstimated1.58B params

Run with ToolPiper

Qwen3.5 9B Claude 4.6 Opus Reasoning Distilled v2

Reasoning · jackrong · 2026-03-16

Q8_0Excellent

11.3 GB47% of RAM~17 tok/sEstimated9.65B params

Run with ToolPiper

EXAONE Deep 2.4B

General · lgai-exaone · 2025-03-12

Q8_0Excellent

3.2 GB13% of RAM~67 tok/sEstimated2.41B params

Run with ToolPiper

EXAONE 4.0 1.2B

General · LG AI · 2025-07-15

Q8_0Excellent

1.8 GB8% of RAM~134 tok/sEstimated1.2B params

Run with ToolPiper

General · raidium · 2026-06-15

Q8_0Excellent

0.5 GB2% of RAM~8,040 tok/sEstimated0.02B params

Run with ToolPiper

embeddinggemma GTAIDE 300m 2605

Embedding · taide · 2026-06-12

Q8_0Excellent

0.8 GB3% of RAM~536 tok/sEstimated0.3B params

Run with ToolPiper

General · Alibaba · 2025-04-27

Q8_0Excellent

1.3 GB6% of RAM~214 tok/sEstimated0.75B params

Run with ToolPiper

General · Alibaba · 2025-04-27

Q8_0Excellent

2.8 GB12% of RAM~79 tok/sEstimated2.03B params

Run with ToolPiper

Multimodal · zai-org

Q8_0Excellent

2.0 GB8% of RAM~121 tok/sEstimated1.33B params

Run with ToolPiper

Qwen3 VL 2B Instruct

Multimodal · Alibaba

Q8_0Excellent

2.9 GB12% of RAM~75 tok/sEstimated2.13B params

Run with ToolPiper

General · Alibaba

Q8_0Excellent

2.2 GB9% of RAM~104 tok/sEstimated1.54B params

Run with ToolPiper

General · Alibaba

Q8_0Excellent

1.0 GB4% of RAM~328 tok/sEstimated0.49B params

Run with ToolPiper

Multimodal · openbmb

Q8_0Excellent

2.0 GB8% of RAM~124 tok/sEstimated1.3B params

Run with ToolPiper

DeepSeek R1 Distill Qwen 1.5B

Reasoning · DeepSeek

Q8_0Excellent

2.5 GB10% of RAM~90 tok/sEstimated1.78B params

Run with ToolPiper

Multimodal · rednote-hilab

Q8_0Excellent

3.9 GB16% of RAM~53 tok/sEstimated3.04B params

Run with ToolPiper

Multimodal · datalab-to

Q8_0Excellent

1.3 GB5% of RAM~233 tok/sEstimated0.69B params

Run with ToolPiper

General · openbmb

Q8_0Excellent

1.7 GB7% of RAM~149 tok/sEstimated1.08B params

Run with ToolPiper

Multimodal · rednote-hilab

Q8_0Excellent

3.9 GB16% of RAM~53 tok/sEstimated3.04B params

Run with ToolPiper

General · hmellor

Q8_0Excellent

1.9 GB8% of RAM~130 tok/sEstimated1.24B params

Run with ToolPiper

distil lfm25 shellper

General · distil-labs

Q8_0Excellent

0.9 GB4% of RAM~459 tok/sEstimated0.35B params

Run with ToolPiper

OTel LLM 1.2B IT

General · farbodtavakkoli

Q8_0Excellent

1.8 GB8% of RAM~133 tok/sEstimated1.21B params

Run with ToolPiper

General · Liquid AI

Q8_0Excellent

9.9 GB41% of RAMBenchmark needed8.47B params

Run with ToolPiper

granite 4.0 tiny preview

General · ibm-granite

Q8_0Excellent

7.9 GB33% of RAMBenchmark needed6.67B params

Run with ToolPiper

reformer crime and punishment

General · Google

Q8_0Excellent

0.5 GB2% of RAM~16,081 tok/sEstimated0.01B params

Run with ToolPiper

VideoLLaMA3 2B Image HF

Multimodal · lkhl

Q8_0Excellent

2.7 GB11% of RAM~82 tok/sEstimated1.96B params

Run with ToolPiper

General · jinaai

Q8_0Excellent

2.2 GB9% of RAM~104 tok/sEstimated1.54B params

Run with ToolPiper

Qwen3 VL 2B Thinking

General · Alibaba

Q8_0Excellent

2.9 GB12% of RAM~75 tok/sEstimated2.13B params

Run with ToolPiper

typhoon ocr1.5 2b

Reasoning · typhoon-ai

Q8_0Excellent

2.9 GB12% of RAM~75 tok/sEstimated2.13B params

Run with ToolPiper

Solar Open 100B

General · Upstage

Q8_0Excellent

9.5 GB40% of RAMBenchmark needed8.05B params

Run with ToolPiper

gpt oss safeguard 120b

General · openai

Q8_0Excellent

3.1 GB13% of RAMBenchmark needed2.37B params

Run with ToolPiper

PaddleOCR VL 1.5

General · paddlepaddle

Q8_0Excellent

1.6 GB7% of RAM~168 tok/sEstimated0.96B params

Run with ToolPiper

LFM2.5 350M Base

General · Liquid AI

Q8_0Excellent

0.9 GB4% of RAM~459 tok/sEstimated0.35B params

Run with ToolPiper

General · pfnet

Q8_0Excellent

1.9 GB8% of RAM~125 tok/sEstimated1.29B params

Run with ToolPiper

MiniCPM5 1B SFT

General · openbmb

Q8_0Excellent

1.7 GB7% of RAM~149 tok/sEstimated1.08B params

Run with ToolPiper

ERNIE 4.5 0.3B PT

General · baidu

Q8_0Excellent

0.9 GB4% of RAM~447 tok/sEstimated0.36B params

Run with ToolPiper

PARD Llama 3.2 1B

General · amd

Q8_0Excellent

2.2 GB9% of RAM~107 tok/sEstimated1.5B params

Run with ToolPiper

General · bytedance-seed

Q8_0Excellent

11.0 GB46% of RAMBenchmark needed9.37B params

Run with ToolPiper

Trinity Nano Preview

General · arcee-ai

Q8_0Excellent

7.3 GB31% of RAMBenchmark needed6.12B params

Run with ToolPiper

Orpo Llama 3.2 1B 15k

General · adamlucek

Q8_0Excellent

1.9 GB8% of RAM~130 tok/sEstimated1.24B params

Run with ToolPiper

llama 3.2 1b code instruct

Coding · shahriarferdoush

Q8_0Excellent

1.9 GB8% of RAM~130 tok/sEstimated1.24B params

Run with ToolPiper

Llama 3.2 1B Aegis SFT DPO

General · ahczhg

Q8_0Excellent

1.9 GB8% of RAM~130 tok/sEstimated1.24B params

Run with ToolPiper

CyberXP_Agent_Llama_3.2_1B

General · abaryan

Q8_0Excellent

1.9 GB8% of RAM~130 tok/sEstimated1.24B params

Run with ToolPiper

General · etherll

Q8_0Excellent

1.3 GB6% of RAM~217 tok/sEstimated0.74B params

Run with ToolPiper

OTel LLM 20B IT

General · farbodtavakkoli

Q8_0Excellent

2.5 GB10% of RAMBenchmark needed1.77B params

Run with ToolPiper

Qwen3 4B Kimi2.5 Reasoning Distilled

Reasoning · khazarai

Q8_0Excellent

4.0 GB17% of RAM~51 tok/sEstimated3.13B params

Run with ToolPiper

General · kamilamila

Q8_0Excellent

1.2 GB5% of RAM~259 tok/sEstimated0.62B params

Run with ToolPiper

transcription cleanup llama3.2 1b

General · getonit

Q8_0Excellent

2.2 GB9% of RAM~107 tok/sEstimated1.5B params

Run with ToolPiper

General · paddlepaddle

Q8_0Excellent

1.6 GB7% of RAM~168 tok/sEstimated0.96B params

Run with ToolPiper

DeepScaleR 1.5B Preview

General · agentica-org

Q8_0Excellent

2.5 GB10% of RAM~90 tok/sEstimated1.78B params

Run with ToolPiper

SEX_ROLEPLAY 3.2 1B

General · novaciano

Q8_0Excellent

2.2 GB9% of RAM~107 tok/sEstimated1.5B params

Run with ToolPiper

Qwen3 VL 2B RRG SFT

General · dmusingu

Q8_0Excellent

2.9 GB12% of RAM~75 tok/sEstimated2.13B params

Run with ToolPiper

JiRackTernary_1b

General · kgrabko

Q8_0Excellent

2.2 GB9% of RAM~107 tok/sEstimated1.5B params

Run with ToolPiper

LFM2.5 350M home assistant sft

General · ordenwills

Q8_0Excellent

0.9 GB4% of RAM~459 tok/sEstimated0.35B params

Run with ToolPiper

Recurrent Llama 3.2 train recurrence 32

General · smcleish

Q8_0Excellent

2.1 GB9% of RAM~116 tok/sEstimated1.39B params

Run with ToolPiper

llama3.2_1b_2025_uncensored_v2

General · carsenk

Q8_0Excellent

1.9 GB8% of RAM~130 tok/sEstimated1.24B params

Run with ToolPiper

OpenReasoning Nemotron 1.5B

Reasoning · nvidia

Q8_0Excellent

2.2 GB9% of RAM~104 tok/sEstimated1.54B params

Run with ToolPiper

Miss MARTHA hot POCKET edition 2B OMNI

General · zero-point-ai

Q8_0Excellent

3.0 GB13% of RAM~71 tok/sEstimated2.27B params

Run with ToolPiper

granite 3.1 1b a400m base

General · ibm-granite

Q8_0Excellent

2.0 GB8% of RAMBenchmark needed1.33B params

Run with ToolPiper

MiniCPM V 4.6 Thinking

General · openbmb

Q8_0Excellent

2.0 GB8% of RAM~124 tok/sEstimated1.3B params

Run with ToolPiper

granite 4.0 h 1b

General · ibm-granite

Q8_0Excellent

2.1 GB9% of RAM~110 tok/sEstimated1.46B params

Run with ToolPiper

MiniMax M2.7 Small JANGTQ

General · osaurusai

Q8_0Excellent

11.3 GB47% of RAMBenchmark needed9.65B params

Run with ToolPiper

gpt oss 120b lora merged redux

General · pyoakum

Q8_0Excellent

6.5 GB27% of RAMBenchmark needed5.35B params

Run with ToolPiper

granite 3.1 3b a800m base

General · ibm-granite

Q8_0Excellent

4.2 GB17% of RAMBenchmark needed3.3B params

Run with ToolPiper

MiniCPM V 4.6 Abliterated AND Disinhibited

General · treadon

Q8_0Excellent

2.0 GB8% of RAM~124 tok/sEstimated1.3B params

Run with ToolPiper

General · tencent

Q8_0Excellent

2.7 GB11% of RAM~82 tok/sEstimated1.96B params

Run with ToolPiper

General · skis-ai-research

Q8_0Excellent

1.8 GB8% of RAM~137 tok/sEstimated1.17B params

Run with ToolPiper

General · menlo

Q8_0Excellent

2.4 GB10% of RAM~93 tok/sEstimated1.72B params

Run with ToolPiper

General · thkim0305

Q8_0Excellent

1.6 GB7% of RAM~161 tok/sEstimated1B params

Run with ToolPiper

General · magistrtheone

Q8_0Excellent

11.5 GB48% of RAMBenchmark needed9.87B params

Run with ToolPiper

Qwen3.5 0.8B Claude 4.6 Opus Reasoning Distilled

Reasoning · jackrong

Q8_0Excellent

1.5 GB6% of RAM~185 tok/sEstimated0.87B params

Run with ToolPiper

Huihui Qwen3.5 2B abliterated

General · huihui-ai

Q8_0Excellent

3.0 GB13% of RAM~71 tok/sEstimated2.27B params

Run with ToolPiper

Qwen3.5 0.8B Coder Calude Full

Coding · rahul7star

Q8_0Excellent

1.5 GB6% of RAM~185 tok/sEstimated0.87B params

Run with ToolPiper

UI Venus 1.5 2B

General · inclusionai

Q8_0Excellent

3.2 GB13% of RAM~66 tok/sEstimated2.44B params

Run with ToolPiper

Falcon H1 1.5B Base

General · TII

Q8_0Excellent

2.2 GB9% of RAM~104 tok/sEstimated1.55B params

Run with ToolPiper

Qwen3 Coder Next DFlash

Coding · z-lab

Q8_0Excellent

1.7 GB7% of RAM~149 tok/sEstimated1.08B params

Run with ToolPiper

Nemotron 3 Nano Omni 30B A3B JANGTQ4

General · osaurusai

Q8_0Excellent

6.9 GB29% of RAMBenchmark needed5.75B params

Run with ToolPiper

LLAMA 3.2 1B OpenHermes2.5

General · artificialguybr

Q8_0Excellent

1.9 GB8% of RAM~130 tok/sEstimated1.24B params

Run with ToolPiper

Dayhoff 170m GR

General · Microsoft

Q8_0Excellent

0.7 GB3% of RAMBenchmark needed0.17B params

Run with ToolPiper

evolai qwen2.5 1.5b

General · roystar

Q8_0Excellent

2.2 GB9% of RAM~104 tok/sEstimated1.54B params

Run with ToolPiper

VibeThinker 1.5B

General · weiboai

Q8_0Excellent

2.5 GB10% of RAM~90 tok/sEstimated1.78B params

Run with ToolPiper

Dayhoff 170m UR90

General · Microsoft

Q8_0Excellent

0.7 GB3% of RAMBenchmark needed0.17B params

Run with ToolPiper

AI21 Jamba Reasoning 3B

Reasoning · ai21labs

Q8_0Excellent

4.1 GB17% of RAMBenchmark needed3.2B params

Run with ToolPiper

Falcon H1 1.5B Deep Base

General · TII

Q8_0Excellent

2.2 GB9% of RAM~104 tok/sEstimated1.55B params

Run with ToolPiper

Hunyuan 0.5B Pretrain

General · tencent

Q8_0Excellent

1.1 GB5% of RAM~298 tok/sEstimated0.54B params

Run with ToolPiper

General · primeintellect

Q8_0Excellent

1.1 GB5% of RAMBenchmark needed0.54B params

Run with ToolPiper

General · Alibaba · 2025-04-27

Q8_0Excellent

5.0 GB21% of RAM~40 tok/sEstimated4.02B params

Run with ToolPiper

Multimodal · Alibaba · 2026-02-27

Q8_0Excellent

11.3 GB47% of RAM~17 tok/sEstimated9.65B params

Run with ToolPiper

Qwen3 VL 4B Instruct

Multimodal · Alibaba

Q8_0Excellent

5.5 GB23% of RAM~36 tok/sEstimated4.44B params

Run with ToolPiper

Multimodal · datalab-to

Q8_0Excellent

6.4 GB27% of RAM~30 tok/sEstimated5.3B params

Run with ToolPiper

Phi 3.5 vision instruct

Multimodal · Microsoft

Q8_0Excellent

5.1 GB21% of RAM~39 tok/sEstimated4.15B params

Run with ToolPiper

General · ibm-granite

Q8_0Excellent

4.3 GB18% of RAM~47 tok/sEstimated3.4B params

Run with ToolPiper

Nanonets OCR2 3B

Multimodal · nanonets

Q8_0Excellent

4.7 GB20% of RAM~43 tok/sEstimated3.75B params

Run with ToolPiper

Qwen3.5 9B Base

Multimodal · Alibaba · 2026-02-26

Q8_0Excellent

11.3 GB47% of RAM~17 tok/sEstimated9.65B params

Run with ToolPiper

General · nanonets

Q8_0Excellent

4.7 GB20% of RAM~43 tok/sEstimated3.75B params

Run with ToolPiper

granite vision 4.1 4b

Multimodal · ibm-granite

Q8_0Excellent

5.0 GB21% of RAM~40 tok/sEstimated4B params

Run with ToolPiper

Multimodal · typhoon-ai

Q8_0Excellent

4.7 GB20% of RAM~43 tok/sEstimated3.75B params

Run with ToolPiper

internlm2_5 step prover critic

General · internlm

Q8_0Excellent

2.1 GB9% of RAM~115 tok/sEstimated1.4B params

Run with ToolPiper

Josiefied Qwen3 VL 4B Instruct abliterated beta v1

Multimodal · goekdeniz-guelmez

Q8_0Excellent

5.5 GB23% of RAM~36 tok/sEstimated4.44B params

Run with ToolPiper

General · kristaller486

Q8_0Excellent

3.9 GB16% of RAM~53 tok/sEstimated3.04B params

Run with ToolPiper

HTML Pruner Phi 3.8B

General · zstanjj

Q8_0Excellent

4.8 GB20% of RAM~42 tok/sEstimated3.82B params

Run with ToolPiper

granite 4.1 3b base

General · ibm-granite

Q8_0Excellent

4.3 GB18% of RAM~47 tok/sEstimated3.4B params

Run with ToolPiper

General · weiboai

Q8_0Excellent

3.9 GB16% of RAM~52 tok/sEstimated3.09B params

Run with ToolPiper

General · x-izhang

Q8_0Excellent

4.1 GB17% of RAM~49 tok/sEstimated3.25B params

Run with ToolPiper

General · bytedance

Q8_0Excellent

2.7 GB11% of RAM~80 tok/sEstimated2.01B params

Run with ToolPiper

granite 4.0 micro base

General · ibm-granite

Q8_0Excellent

4.3 GB18% of RAM~47 tok/sEstimated3.4B params

Run with ToolPiper

Ouro 2.6B Thinking

General · bytedance

Q8_0Excellent

3.5 GB14% of RAM~60 tok/sEstimated2.67B params

Run with ToolPiper

General · stanford-oval

Q8_0Excellent

4.7 GB20% of RAM~43 tok/sEstimated3.75B params

Run with ToolPiper

Flow Judge v0.1

General · flowaicom

Q8_0Excellent

4.8 GB20% of RAM~42 tok/sEstimated3.82B params

Run with ToolPiper

llama 3.2 Korean Bllossom 3B

General · bllossom

Q8_0Excellent

4.1 GB17% of RAM~50 tok/sEstimated3.21B params

Run with ToolPiper

InternVL3 2B hf

General · opengvlab

Q8_0Excellent

2.8 GB12% of RAM~77 tok/sEstimated2.09B params

Run with ToolPiper

Kimi K2.5 DFlash

General · z-lab

Q8_0Excellent

4.4 GB18% of RAM~46 tok/sEstimated3.48B params

Run with ToolPiper

Ouro 1.4B Thinking

General · bytedance

Q8_0Excellent

2.1 GB9% of RAM~112 tok/sEstimated1.43B params

Run with ToolPiper

General · radheneev

Q8_0Excellent

4.1 GB17% of RAM~50 tok/sEstimated3.21B params

Run with ToolPiper

Model not in the list? Paste a HuggingFace URL or ID for an instant fit check.

Frequently Asked Questions

How much RAM do I need to run LLMs on a Mac?

It depends on the model size and quantization. A 7B parameter model at Q4 quantization needs about 5 GB of RAM, while a 70B model needs 40+ GB. Apple Silicon Macs use unified memory, so your entire RAM pool is available for model weights — no separate VRAM required.

Can I run a 70B model on a MacBook Air?

Not comfortably. A 70B model at Q4 quantization needs about 40 GB of RAM. The MacBook Air maxes out at 24-32 GB depending on the generation. You'd need a Mac Studio or MacBook Pro with 48+ GB for a 70B model to run well.

What's the fastest LLM I can run on my Mac?

Speed depends on your chip's memory bandwidth and the model size. Smaller models (3-7B) run fastest — expect 40-70+ tokens per second on M2 Pro or better. Use the calculator above to see estimated speeds for your specific Mac.

What does quantization mean for model quality?

Quantization reduces model precision to use less memory. Q8 (8-bit) is nearly lossless. Q4 (4-bit) reduces memory by ~75% with minor quality loss — it's the sweet spot for most users. Q2 (2-bit) saves the most memory but noticeably degrades output quality.

How is Apple Silicon different from NVIDIA for LLMs?

Apple Silicon uses unified memory — CPU and GPU share the same RAM pool. A Mac with 32 GB can load a 28 GB model directly. On NVIDIA systems, you're limited by GPU VRAM (typically 8-24 GB on consumer cards), even if the PC has 64 GB of system RAM.

Does ToolPiper use GPU or CPU for inference?

ToolPiper uses Metal GPU acceleration via llama.cpp for LLM inference on Apple Silicon. The GPU and CPU share unified memory, so there's no data transfer overhead. The Neural Engine (ANE) is used for specific tasks like super-resolution and pose detection.

Can I run multiple models at the same time?

Yes, if you have enough RAM. ToolPiper manages model loading and can keep multiple models in memory simultaneously. When memory gets tight, it automatically evicts the least recently used model to make room for a new one.

What's the difference between GGUF and other formats?

GGUF is the standard format for running quantized models with llama.cpp (and ToolPiper). It supports all quantization levels and runs on CPU+GPU. MLX is Apple's format optimized for Apple Silicon. AWQ and GPTQ are NVIDIA-focused formats that don't run natively on Mac.

Model database updated: 2026-07-24 · 3641 models