← Back to all models

Qwen3 4B Kimi2.5 Reasoning Distilled

Reasoning model by khazarai · 3.13B parameters

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

Runs Excellently

Qwen3 4B Kimi2.5 Reasoning Distilled fits comfortably in your 24 GB Mac using Q8_0 quantization, using 17% of your RAM.

~51 tok/s

Q8_0 · 4.0 GB · Estimated

Quantization Options

QuantizationMemorySpeedFits?
Q8_0 Recommended 4.0 GB~51 tok/s✓
Q6_K 3.2 GB~67 tok/s✓
Q5_K_M 2.8 GB~79 tok/s✓
Q4_K_M 2.5 GB~93 tok/s✓
Q3_K_M 2.2 GB~112 tok/s✓
Q2_K 1.9 GB~146 tok/s✓

Specifications

Parameters3.1B
Architectureqwen3
Context Length262K
CategoryReasoning
Capabilitiestool_use
Formatgguf
Minimum RAM1.7 GB
HuggingFace Downloads14,339

GGUF Sources

khazarai
View on HuggingFace →

Which Mac Can Run Qwen3 4B Kimi2.5 Reasoning Distilled?

Minimum Mac

MacBook Air — M2 8GB

Q8_0 · ~17 tok/s · 50% RAM

MacQuanttok/sRAM %
Mac Studio · M3 Ultra 96GB Q8_0 ~137 4%
Mac Studio · M3 Ultra 256GB Q8_0 ~137 2%
Mac Studio · M3 Ultra 512GB Q8_0 ~137 1%
Mac Studio · M1 Ultra 64GB Q8_0 ~134 6%
Mac Studio · M1 Ultra 128GB Q8_0 ~134 3%
Mac Studio · M2 Ultra 64GB Q8_0 ~134 6%
Mac Studio · M2 Ultra 128GB Q8_0 ~134 3%
Mac Studio · M2 Ultra 192GB Q8_0 ~134 2%
MacBook Pro 14" · M5 Max 36GB Q8_0 ~103 11%
MacBook Pro 14" · M5 Max 48GB Q8_0 ~103 8%
MacBook Pro 14" · M5 Max 64GB Q8_0 ~103 6%
MacBook Pro 14" · M5 Max 128GB Q8_0 ~103 3%
MacBook Pro 16" · M5 Max 36GB Q8_0 ~103 11%
MacBook Pro 16" · M5 Max 48GB Q8_0 ~103 8%
MacBook Pro 16" · M5 Max 64GB Q8_0 ~103 6%
MacBook Pro 16" · M5 Max 128GB Q8_0 ~103 3%
MacBook Pro 14" · M4 Max 36GB Q8_0 ~91 11%
MacBook Pro 14" · M4 Max 48GB Q8_0 ~91 8%
MacBook Pro 14" · M4 Max 64GB Q8_0 ~91 6%
MacBook Pro 14" · M4 Max 128GB Q8_0 ~91 3%
MacBook Pro 16" · M4 Max 36GB Q8_0 ~91 11%
MacBook Pro 16" · M4 Max 48GB Q8_0 ~91 8%
MacBook Pro 16" · M4 Max 64GB Q8_0 ~91 6%
MacBook Pro 16" · M4 Max 128GB Q8_0 ~91 3%
Mac Studio · M4 Max 36GB Q8_0 ~91 11%
Mac Studio · M4 Max 48GB Q8_0 ~91 8%
Mac Studio · M4 Max 64GB Q8_0 ~91 6%
Mac Studio · M4 Max 128GB Q8_0 ~91 3%
MacBook Pro 14" · M1 Max 32GB Q8_0 ~67 12%
MacBook Pro 14" · M1 Max 64GB Q8_0 ~67 6%
MacBook Pro 14" · M2 Max 32GB Q8_0 ~67 12%
MacBook Pro 14" · M2 Max 64GB Q8_0 ~67 6%
MacBook Pro 14" · M2 Max 96GB Q8_0 ~67 4%
MacBook Pro 14" · M3 Max 36GB Q8_0 ~67 11%
MacBook Pro 14" · M3 Max 48GB Q8_0 ~67 8%
MacBook Pro 14" · M3 Max 64GB Q8_0 ~67 6%
MacBook Pro 14" · M3 Max 96GB Q8_0 ~67 4%
MacBook Pro 14" · M3 Max 128GB Q8_0 ~67 3%
MacBook Pro 16" · M1 Max 32GB Q8_0 ~67 12%
MacBook Pro 16" · M1 Max 64GB Q8_0 ~67 6%
MacBook Pro 16" · M2 Max 32GB Q8_0 ~67 12%
MacBook Pro 16" · M2 Max 64GB Q8_0 ~67 6%
MacBook Pro 16" · M2 Max 96GB Q8_0 ~67 4%
MacBook Pro 16" · M3 Max 36GB Q8_0 ~67 11%
MacBook Pro 16" · M3 Max 48GB Q8_0 ~67 8%
MacBook Pro 16" · M3 Max 64GB Q8_0 ~67 6%
MacBook Pro 16" · M3 Max 96GB Q8_0 ~67 4%
MacBook Pro 16" · M3 Max 128GB Q8_0 ~67 3%
Mac Studio · M1 Max 32GB Q8_0 ~67 12%
Mac Studio · M1 Max 64GB Q8_0 ~67 6%
Mac Studio · M2 Max 32GB Q8_0 ~67 12%
Mac Studio · M2 Max 64GB Q8_0 ~67 6%
Mac Studio · M2 Max 96GB Q8_0 ~67 4%
MacBook Pro 14" · M5 Pro 24GB Q8_0 ~51 17%
MacBook Pro 14" · M5 Pro 48GB Q8_0 ~51 8%
MacBook Pro 14" · M5 Pro 64GB Q8_0 ~51 6%
MacBook Pro 16" · M5 Pro 24GB Q8_0 ~51 17%
MacBook Pro 16" · M5 Pro 48GB Q8_0 ~51 8%
MacBook Pro 16" · M5 Pro 64GB Q8_0 ~51 6%
MacBook Pro 14" · M4 Pro 24GB Q8_0 ~46 17%
MacBook Pro 14" · M4 Pro 48GB Q8_0 ~46 8%
MacBook Pro 16" · M4 Pro 24GB Q8_0 ~46 17%
MacBook Pro 16" · M4 Pro 48GB Q8_0 ~46 8%
Mac mini · M4 Pro 24GB Q8_0 ~46 17%
Mac mini · M4 Pro 48GB Q8_0 ~46 8%
Mac mini · M4 Pro 64GB Q8_0 ~46 6%
MacBook Pro 14" · M1 Pro 16GB Q8_0 ~33 25%
MacBook Pro 14" · M1 Pro 32GB Q8_0 ~33 12%
MacBook Pro 14" · M2 Pro 16GB Q8_0 ~33 25%
MacBook Pro 14" · M2 Pro 32GB Q8_0 ~33 12%
MacBook Pro 16" · M1 Pro 16GB Q8_0 ~33 25%
MacBook Pro 16" · M1 Pro 32GB Q8_0 ~33 12%
MacBook Pro 16" · M2 Pro 16GB Q8_0 ~33 25%
MacBook Pro 16" · M2 Pro 32GB Q8_0 ~33 12%
Mac mini · M2 Pro 16GB Q8_0 ~33 25%
Mac mini · M2 Pro 32GB Q8_0 ~33 12%
MacBook Air · M5 16GB Q8_0 ~26 25%
MacBook Air · M5 24GB Q8_0 ~26 17%
MacBook Air · M5 32GB Q8_0 ~26 12%
MacBook Pro 14" · M5 16GB Q8_0 ~26 25%
MacBook Pro 14" · M5 24GB Q8_0 ~26 17%
MacBook Pro 14" · M5 32GB Q8_0 ~26 12%
MacBook Pro 14" · M3 Pro 18GB Q8_0 ~25 22%
MacBook Pro 14" · M3 Pro 36GB Q8_0 ~25 11%
MacBook Pro 16" · M3 Pro 18GB Q8_0 ~25 22%
MacBook Pro 16" · M3 Pro 36GB Q8_0 ~25 11%
MacBook Air · M4 16GB Q8_0 ~20 25%
MacBook Air · M4 24GB Q8_0 ~20 17%
MacBook Air · M4 32GB Q8_0 ~20 12%
MacBook Pro 14" · M4 16GB Q8_0 ~20 25%
MacBook Pro 14" · M4 24GB Q8_0 ~20 17%
MacBook Pro 14" · M4 32GB Q8_0 ~20 12%
Mac mini · M4 16GB Q8_0 ~20 25%
Mac mini · M4 24GB Q8_0 ~20 17%
Mac mini · M4 32GB Q8_0 ~20 12%
iMac · M4 16GB Q8_0 ~20 25%
iMac · M4 24GB Q8_0 ~20 17%
iMac · M4 32GB Q8_0 ~20 12%
MacBook Air · M2 8GB Q8_0 ~17 50%
MacBook Air · M2 16GB Q8_0 ~17 25%
MacBook Air · M2 24GB Q8_0 ~17 17%
MacBook Air · M3 8GB Q8_0 ~17 50%
MacBook Air · M3 16GB Q8_0 ~17 25%
MacBook Air · M3 24GB Q8_0 ~17 17%
MacBook Pro 14" · M3 8GB Q8_0 ~17 50%
MacBook Pro 14" · M3 16GB Q8_0 ~17 25%
MacBook Pro 14" · M3 24GB Q8_0 ~17 17%
Mac mini · M2 8GB Q8_0 ~17 50%
Mac mini · M2 16GB Q8_0 ~17 25%
Mac mini · M2 24GB Q8_0 ~17 17%
iMac · M3 8GB Q8_0 ~17 50%
iMac · M3 16GB Q8_0 ~17 25%
iMac · M3 24GB Q8_0 ~17 17%
MacBook Air · M1 8GB Q8_0 ~11 50%
MacBook Air · M1 16GB Q8_0 ~11 25%
Mac mini · M1 8GB Q8_0 ~11 50%
Mac mini · M1 16GB Q8_0 ~11 25%
iMac · M1 8GB Q8_0 ~11 50%
iMac · M1 16GB Q8_0 ~11 25%

Models similar to Qwen3 4B Kimi2.5 Reasoning Distilled

Closest matches by use case and parameter count.

Run Qwen3 4B Kimi2.5 Reasoning Distilled locally on your Mac

ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.

Get ToolPiper — Free