Qwen 3.6 35B A3B needs ~56.9 GB VRAM. AMD Instinct MI350X 288GB has 288.0 GB. With Q4_K_M quantization, expect ~742 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
Fit status
Runs well
Decode
742.2 tok/s
TTFT
350 ms
Safe context
262K
Memory
56.9 GB / 288.0 GB
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 | S | Runs well | 742.2 tok/s | 350 ms | 262K |
| Coding | S | Runs well | 742.2 tok/s | 350 ms | 262K |
| Agentic Coding | S | Runs well | 742.2 tok/s | 379 ms | 262K |
| Reasoning | S | Runs well | 742.2 tok/s | 350 ms | 262K |
| RAG | S | Runs well | 742.2 tok/s | 474 ms | 262K |
How Qwen 3.6 35B A3B (35B params) fits at each quantization level on AMD Instinct MI350X 288GB (288.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 13.7 GB | Low | A78 |
Q3_K_S | 3 | 17.2 GB | Low | A79 |
NVFP4 | 4 |
Copy-paste commands to run Qwen 3.6 35B A3B on your machine.
Run
docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
--hf-repo "Qwen/Qwen3.6-35B-A3B" \
--hf-file "Qwen3.6-35B-A3B-Q4_K_M.gguf" \
-c 4096 -ngl 99Your hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
| 123B | S | 84.6 tok/s | ||
| 122B | S |
Yes, AMD Instinct MI350X 288GB can run Qwen 3.6 35B A3B with a S grade (Runs well). Expected decode speed: 742.2 tok/s.
Qwen 3.6 35B A3B (35B parameters) requires approximately 56.9 GB of memory with Q4_K_M quantization.
The recommended quantization for Qwen 3.6 35B A3B is Q4_K_M, which balances quality and memory efficiency.
On AMD Instinct MI350X 288GB, Qwen 3.6 35B A3B achieves approximately 742.2 tokens per second decode speed with a time-to-first-token of 350ms using Q4_K_M quantization.
For coding workloads, Qwen 3.6 35B A3B on AMD Instinct MI350X 288GB receives a S grade with 742.2 tok/s and 262K context.
On AMD Instinct MI350X 288GB, Qwen 3.6 35B A3B can safely use up to 262K tokens of context. The model's official context limit is 262K, 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/qwen-3.6-35b-a3b-on-instinct-mi350x-288gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview:
19.6 GB |
| Medium |
| A79 |
Q4_K_M | 4 | 21.3 GB | Medium | A79 |
Q5_K_M | 5 | 25.2 GB | High | A79 |
Q6_K | 6 | 28.7 GB | High | A80 |
Q8_0 | 8 | 37.5 GB | Very High | A80 |
F16Best for your GPU | 16 | 71.8 GB | Maximum | A83 |
| 234.8 tok/s |
| 284B | S | 125.8 tok/s |