Can I run it?

Can I run Qwen3 VL 4B Instruct on Apple M4?

Runs

Runs fully in unified memory on your Apple M4 at BF16, 8K context, about 7.1–9.7 tok/s. Weights 7.50 GB plus 1.13 GB of KV cache — 9.00 GB of 11.0 GB usable. Up to 16K context still fits.

Qwen3 VL 4B Instruct details · Apple M4 page · How this estimate is made

Run commands

llama-server -hf unsloth/Qwen3-VL-4B-Instruct-GGUF:BF16 -c 8192 -ngl 36

ollama run qwen3

lms get unsloth/Qwen3-VL-4B-Instruct-GGUF
# Then load quant BF16

Assumptions

• Estimate, not a benchmark. Decode speed uses a memory-bandwidth model at 55–75% of peak.
• KV cache is FP16. Engine overhead assumes llama.cpp (0.3 GB + 1% of the weights). Ollama is closer to 0.9 GB + 3%, LM Studio closer to 1 GB + 3%.
• BF16 size is the real GGUF file size from Hugging Face.
• Unified memory uses 75% for the GPU by default, and always leaves about 5 GB for the OS.
• Speed is quoted at 8K context, not at the maximum context that still fits.

Larger models that also fit

• Can I run Qwen3.8 27B on Apple M4? — Tight fit, UD-Q2_K_XL, 6.4–8.7 tok/s
• Can I run gemma 4 12b it on Apple M4? — Tight fit, Q6_K, 5.1–6.9 tok/s
• Can I run Qwen3.5 9B on Apple M4? — Tight fit, Q8_0, 6.7–9.2 tok/s

Updated 2026-10-24. Profile on this page is the device default.