Raises estimated decode speed by about 168%.
Adds memory headroom for longer context windows and future model growth.
~$30,000 MSRP
Qwen3.5 122B A10B needs ~84.9 GB VRAM. RTX PRO 6000 Blackwell Workstation Edition 96GB has 96.0 GB. With Q3_K_M quantization, expect ~23 tok/s.
Operating mode
Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.
Current mode
Balanced
Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.
Select quantization to explore
179.2 GB over capacity — needs offload or smaller quantization
Fit status
Too heavy
Decode
2.0 tok/s
TTFT
96800 ms
Safe context
4K
Memory
275.2 GB / 96.0 GB
Offload
70%
This setup is broadly balanced for this model.
No major red flags
This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | C | Runs well | 23.4 tok/s | 4509 ms | 28K |
| Coding | C | Tight fit | 23.4 tok/s | 8267 ms | 28K |
| Agentic Coding | C | Runs with offload (needs ~1.9 GB host RAM) | 16.8 tok/s | 16804 ms | 28K |
| Reasoning | C | Tight fit | 23.4 tok/s | 9770 ms | 28K |
| RAG | C | Runs with offload (needs ~1.9 GB host RAM) | 16.8 tok/s | 21005 ms |
How Qwen3.5 122B A10B (122B params) fits at each quantization level on RTX PRO 6000 Blackwell Workstation Edition 96GB (96.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 47.6 GB | Low | C48 |
Q3_K_S | 3 | 59.8 GB | Low | C48 |
NVFP4 | 4 |
Copy-paste commands to run Qwen3.5 122B A10B on your machine.
Run
docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
--hf-repo "unsloth/Qwen3.5-122B-A10B-GGUF" \
--hf-file "Qwen3.5-122B-A10B-GGUF-Q3_K_M.gguf" \
-c 4096 -ngl 99Upgrade options
Raises estimated decode speed by about 168%.
Adds memory headroom for longer context windows and future model growth.
~$30,000 MSRP
Raises estimated decode speed by about 168%.
Adds memory headroom for longer context windows and future model growth.
~$30,000 MSRP
Raises estimated decode speed by about 347%.
Adds memory headroom for longer context windows and future model growth.
~$30,000 MSRP
Yes, RTX PRO 6000 Blackwell Workstation Edition 96GB can run Qwen3.5 122B A10B with a C grade (Tight fit). Expected decode speed: 23.4 tok/s.
Qwen3.5 122B A10B (122B parameters) requires approximately 84.9 GB of memory with Q3_K_M quantization.
The recommended quantization for Qwen3.5 122B A10B is Q3_K_M, which balances quality and memory efficiency.
On RTX PRO 6000 Blackwell Workstation Edition 96GB, Qwen3.5 122B A10B achieves approximately 23.4 tokens per second decode speed with a time-to-first-token of 8267ms using Q3_K_M quantization.
For coding workloads, Qwen3.5 122B A10B on RTX PRO 6000 Blackwell Workstation Edition 96GB receives a C grade with 23.4 tok/s and 28K context.
On RTX PRO 6000 Blackwell Workstation Edition 96GB, Qwen3.5 122B A10B can safely use up to 28K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/hf-unsloth--qwen3-5-122b-a10b-gguf-on-rtx-pro-6000-blackwell-96gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview:
| 28K |
68.3 GB |
| Medium |
| C48 |
Q4_K_MBest for your GPU | 4 | 74.4 GB | Medium | C48 |
Q5_K_M | 5 | 87.8 GB | High | F0 |
Q6_K | 6 | 100.0 GB | High | F0 |
Q8_0 | 8 | 130.5 GB | Very High | F0 |
F16 | 16 | 250.1 GB | Maximum | F0 |