Can I run it?
Can I run Qwen2.5 VL 7B Instruct on Apple M5?
Tight fit
Tight fit fully in unified memory on your Apple M5 at UD-Q8_K_XL, 8K context, about 7.9–11 tok/s. Weights 9.49 GB plus 0.44 GB of KV cache — 10.3 GB of 11.0 GB usable. Up to 16K context still fits.
Best quantUD-Q8_K_XL
Working context8K
Max that fits16K
Speed7.9–11 tok/s
Weights9.49 GB
KV cache0.44 GB
Total10.3 GB
Usable11.0 GB
Qwen2.5 VL 7B Instruct details · Apple M5 page · How this estimate is made
Run commands
llama.cpp
llama-server -hf unsloth/Qwen2.5-VL-7B-Instruct-GGUF:UD-Q8_K_XL -c 8192 -ngl 28
Ollama
ollama run qwen2.5
LM Studio
lms get unsloth/Qwen2.5-VL-7B-Instruct-GGUF # Then load quant UD-Q8_K_XL
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%.
- UD-Q8_K_XL 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 M5? — Tight fit, UD-Q2_K_XL, 8.1–11 tok/s
- Can I run gemma 4 12b it on Apple M5? — Tight fit, Q6_K, 6.5–8.8 tok/s
- Can I run Qwen3.5 9B on Apple M5? — Tight fit, Q8_0, 8.6–12 tok/s
Updated 2026-10-17. Profile on this page is the device default.