Qwen3.5 397B A17B on M3 Ultra 96 GB: VRAM, speed and fit
Qwen3.5 397B A17B at 4-bit needs 229 GB; the M3 Ultra 96 GB can use 72.0 GB. The smallest machine we checked that runs it is the DGX Station GB300.
Text generation · Chat · Ollama / LM Studio
Won’t fit · on M3 Ultra 96 GB · 4-bit (Q4_K_M) · Ollama / LM Studio · Chat
- GPU memory
- 253 GB
- of 96.0 GB
- Context
- 8K
- auto
- Speed
- n/a
- First reply
- n/a
Where the memory goes
- Model
- 228 GB
- Context
- 423 MB
- Overhead
- 869 MB
- OS
- 24.0 GB
- Over by
- 157 GB
- Memory
- 253 GB of 96.0 GB
- Context
- 8K tokens · auto
- Speed
- Doesn’t run here
- Running cost
- Doesn’t run here · $574/mo on a cloud 8× A40
Validation: Not validated
| Check | Target | Result | Status |
|---|---|---|---|
| Fits in GPU memory | 72.0 GB usable | 229 GB needed | Fails |
| Headroom | 5% free | none | Fails |
| Context for chat | 16K or more | – | Not run |
| Writing speed | 15 tok/s or more | – | Not run |
| First reply | under 3 s, 2K prompt | – | Not run |
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
- 4-bit (Q4_K_M)
- Context
- 8K, auto
- Chats at once
- 1
- Use
- Chat
- Runs in
- Ollama / LM Studio
- Hardware
- M3 Ultra 96 GB
- GPU can use
- 72.0 GB of 96.0 GB
Worth trying
- DGX Station GB300: Runs it with 256K context
- 2× H200 NVL: Runs it with 256K context
- M5 Ultra · 512 GB: Runs it with 256K context
Running cost
- At home
- n/a
- Doesn’t run on this machine.
- 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 21, 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
- Mac mini M4 Pro 48 GBToo big
- Mac mini M4 Pro 64 GBToo big
- M4 Max 128 GBRuns
- M5 Max 128 GBRuns
- M3 Ultra 256 GBRuns
- M3 Ultra 512 GBRuns
- M5 Ultra 512 GBRuns
- Ryzen AI Max+ 395 64 GBToo big
All machines: Qwen3.5 397B A17B VRAM requirements. Everything that runs here: what can the M3 Ultra 96 GB run?
Other models that run on M3 Ultra 96 GB
Questions
Can Qwen3.5 397B A17B run on M3 Ultra 96 GB?
Qwen3.5 397B A17B at 4-bit needs 229 GB; the M3 Ultra 96 GB can use 72.0 GB. The smallest machine we checked that runs it is the DGX Station GB300.
Shown at the closest setup. Report VR-1CQAI82, calculated Nov 22, 2026 from published specs, not benchmarked.