Qwen3.5 122B A10B on RTX PRO 5000 Blackwell 48 GB: VRAM, speed and fit
Qwen3.5 122B A10B at 2-bit runs on the RTX PRO 5000 Blackwell 48 GB with 32K of context at about 142 tokens a second.
Text generation · Chat · Ollama / LM Studio
Runs comfortably · on RTX PRO 5000 Blackwell 48 GB · 2-bit (Q2_K) · Ollama / LM Studio · Chat
- GPU memory
- 45.6 GB
- of 48.0 GB
- Context
- 32K
- auto
- Speed
- 142 tok/s
- Very fast
- First reply
- 0.9 s
- 2K prompt
Where the memory goes
- Model
- 43.7 GB
- Context
- 915 MB
- Overhead
- 1.0 GB
- OS
- 0.0 GB
- Free
- 2.4 GB
- Memory
- 45.6 GB of 48.0 GB
- Context
- 32K tokens · auto
- Speed
- 142 tok/s · very fast
- First reply
- 0.9 s for a 2K prompt
- Running cost
- $5.69/mo at home · $66/mo on a cloud 2× RTX A5000
Validation: Validated
| Check | Target | Result | Status |
|---|---|---|---|
| Fits in GPU memory | 48.0 GB usable | 45.6 GB needed | Pass |
| Headroom | 5% free | 2.4 GB free (5%) | Pass |
| Context for chat | 16K or more | 32K | Pass |
| Writing speed | 15 tok/s or more | 142 tok/s | Pass |
| First reply | under 3 s, 2K prompt | 0.9 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 122B A10B
- Parameters
- 125B, 10B active
- Precision
- 2-bit (Q2_K)
- Context
- 32K, auto
- Chats at once
- 1
- Use
- Chat
- Runs in
- Ollama / LM Studio
- Hardware
- RTX PRO 5000 Blackwell 48 GB
- GPU can use
- 48.0 GB of 48.0 GB
Worth trying
- 8-bit cache: Room for 60K context
Running cost
- At home
- $5.69/mo
- 260 W at the wall
- Renting instead
- $66/mo
- 2× RTX A5000 at $0.54/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
- Ollama
ollama run qwen3.5:122b-a10b- llama.cpp
llama-server -hf unsloth/Qwen3.5-122B-A10B-GGUF- vLLM
vllm serve Qwen/Qwen3.5-122B-A10B- MLX (Mac)
mlx_lm.chat --model mlx-community/Qwen3.5-122B-A10B-4bit- Model card
- huggingface.co/Qwen/Qwen3.5-122B-A10B
Qwen3.5 122B A10B on similar machines
- Radeon AI PRO R9700Too big
- RTX 5090Too big
- 2× RTX 3090Just misses
- 2× RTX 4090Just misses
- RTX 6000 AdaRuns
- L40SRuns
- 2× RTX 5090Runs
- 4× RTX 3090Runs
All machines: Qwen3.5 122B A10B VRAM requirements. Everything that runs here: what can the RTX PRO 5000 Blackwell 48 GB run?
Other models that run on RTX PRO 5000 Blackwell 48 GB
Questions
Can Qwen3.5 122B A10B run on RTX PRO 5000 Blackwell 48 GB?
Qwen3.5 122B A10B at 2-bit runs on the RTX PRO 5000 Blackwell 48 GB with 32K of context at about 142 tokens a second.
Report VR-1HPYPRA, calculated Nov 22, 2026 from published specs, not benchmarked.