Qwen3.5 397B A17B on RTX PRO 6000 Blackwell: VRAM, speed and fit
Qwen3.5 397B A17B at 1.6-bit runs on the RTX PRO 6000 Blackwell with 256K of context at about 153 tokens a second.
Text generation · Chat · Ollama / LM Studio
Runs comfortably · on RTX PRO 6000 Blackwell · 1.6-bit (IQ1_S) · Ollama / LM Studio · Chat
- GPU memory
- 86.2 GB
- of 96.0 GB
- Context
- 256K
- auto
- Speed
- 153 tok/s
- 77 when full
- First reply
- 0.8 s
- 2K prompt
Where the memory goes
- Model
- 77.5 GB
- Context
- 7.7 GB
- Overhead
- 1.0 GB
- OS
- 0.0 GB
- Free
- 9.8 GB
- Memory
- 86.2 GB of 96.0 GB
- Context
- 256K tokens · auto
- Speed
- 153 tok/s · 77 when full
- First reply
- 0.8 s for a 2K prompt
- Running cost
- $9.63/mo at home · $131/mo on a cloud 4× RTX A5000
Validation: Validated
| Check | Target | Result | Status |
|---|---|---|---|
| Fits in GPU memory | 96.0 GB usable | 86.2 GB needed | Pass |
| Headroom | 5% free | 9.8 GB free (10%) | Pass |
| Context for chat | 16K or more | 256K | Pass |
| Writing speed | 15 tok/s or more | 153 tok/s | Pass |
| First reply | under 3 s, 2K prompt | 0.8 s | Pass |
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
- 1.6-bit (IQ1_S)
- Context
- 256K, auto
- Chats at once
- 1
- Use
- Chat
- Runs in
- Ollama / LM Studio
- Hardware
- RTX PRO 6000 Blackwell
- GPU can use
- 96.0 GB of 96.0 GB
Running cost
- At home
- $9.63/mo
- 440 W at the wall
- Renting instead
- $131/mo
- 4× RTX A5000 at $1.08/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
- RTX 6000 AdaToo big
- L40SToo big
- 2× RTX 5090Just misses
- 4× RTX 3090Runs
- Mac mini M4 16 GBToo big
- Mac mini M4 24 GBToo big
- Mac mini M4 32 GBToo big
- Mac mini M4 Pro 24 GBToo big
All machines: Qwen3.5 397B A17B VRAM requirements. Everything that runs here: what can the RTX PRO 6000 Blackwell run?
Other models that run on RTX PRO 6000 Blackwell
Questions
Can Qwen3.5 397B A17B run on RTX PRO 6000 Blackwell?
Qwen3.5 397B A17B at 1.6-bit runs on the RTX PRO 6000 Blackwell with 256K of context at about 153 tokens a second.
Report VR-11E6AMX, calculated Nov 22, 2026 from published specs, not benchmarked.