Qwen3.5 397B A17B on M5 Ultra 512 GB: VRAM, speed and fit
Qwen3.5 397B A17B at 6-bit runs on the M5 Ultra 512 GB with 256K of context at about 38 tokens a second.
Text generation · Chat · Ollama / LM Studio
Runs comfortably · on M5 Ultra 512 GB · 6-bit (Q6_K) · Ollama / LM Studio · Chat
- GPU memory
- 445 GB
- of 512 GB
- Context
- 256K
- auto
- Speed
- 38 tok/s
- 27 when full
- First reply
- 3.1 s
- 2K prompt
Where the memory goes
- Model
- 308 GB
- Context
- 7.7 GB
- Overhead
- 869 MB
- OS
- 128 GB
- Free
- 67.4 GB
- Memory
- 445 GB of 512 GB
- Context
- 256K tokens · auto
- Speed
- 38 tok/s · 27 when full
- First reply
- 3.1 s for a 2K prompt
- Running cost
- $5.06/mo at home · $574/mo on a cloud 8× A40
Validation: Validated with conditions
| Check | Target | Result | Status |
|---|---|---|---|
| Fits in GPU memory | 384 GB usable | 317 GB needed | Pass |
| Headroom | 5% free | 67.4 GB free (18%) | Pass |
| Context for chat | 16K or more | 256K | Pass |
| Writing speed | 15 tok/s or more | 38 tok/s | Pass |
| First reply | under 3 s, 2K prompt | 3.1 s | Check |
Targets: a reply you can read along with, a first reply the use case tolerates, and 5% of memory left free. Calculated from published specs, not benchmarked.
The setup
- Model
- Qwen3.5 397B A17B
- Parameters
- 403B, 17B active
- Precision
- 6-bit (Q6_K)
- Context
- 256K, auto
- Chats at once
- 1
- Use
- Chat
- Runs in
- Ollama / LM Studio
- Hardware
- M5 Ultra 512 GB
- GPU can use
- 384 GB of 512 GB
Running cost
- At home
- $5.06/mo
- 231 W at the wall
- Renting instead
- $574/mo
- 8× A40 at $4.72/h
4 h a day, power at $0.18 per kWh, cloud at RunPod on-demand prices as of Nov 22, 2026.
How to run it
- llama.cpp
llama-server -hf unsloth/Qwen3.5-397B-A17B-GGUF- vLLM
vllm serve Qwen/Qwen3.5-397B-A17B- MLX (Mac)
mlx_lm.chat --model mlx-community/Qwen3.5-397B-A17B-4bit- Model card
- huggingface.co/Qwen/Qwen3.5-397B-A17B
Qwen3.5 397B A17B on similar machines
- M5 Max 128 GBRuns
- M3 Ultra 96 GBJust misses
- M3 Ultra 256 GBRuns
- M3 Ultra 512 GBRuns
- Ryzen AI Max+ 395 64 GBToo big
- Ryzen AI Max+ 395 128 GBRuns
- RTX SparkRuns
- DGX SparkRuns
All machines: Qwen3.5 397B A17B VRAM requirements. Everything that runs here: what can the M5 Ultra 512 GB run?
Other models that run on M5 Ultra 512 GB
Questions
Can Qwen3.5 397B A17B run on M5 Ultra 512 GB?
Qwen3.5 397B A17B at 6-bit runs on the M5 Ultra 512 GB with 256K of context at about 38 tokens a second.
Report VR-00XJSB8, calculated Nov 22, 2026 from published specs, not benchmarked.