Can I run it?

Can I run Qwythos 9B v2 on Apple M4 Pro?

Tight fit

Tight fit fully in unified memory on your Apple M4 Pro at BF16, 8K context, about 8.3–11 tok/s. Weights 16.7 GB plus 0.27 GB of KV cache — 17.4 GB of 18.0 GB usable.

Best quantBF16

Working context8K

Max that fits8K

Speed8.3–11 tok/s

Weights16.7 GB

KV cache0.27 GB

Total17.4 GB

Usable18.0 GB

Qwythos 9B v2 details · Apple M4 Pro page · How this estimate is made

Run commands

llama.cpp

llama-server -hf empero-ai/Qwythos-9B-v2-GGUF:BF16 -c 8192 -ngl 32

No matching name in the Ollama library snapshot.

LM Studio

lms get empero-ai/Qwythos-9B-v2-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 Pro? — Tight fit, UD-Q4_K_XL, 8.3–11 tok/s
Can I run gemma 4 12b it on Apple M4 Pro? — Runs, UD-Q8_K_XL, 8.9–12 tok/s
Can I run Qwen3.5 9B on Apple M4 Pro? — Tight fit, BF16, 8.3–11 tok/s

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