Qwen 3.6 35B A3B needs ~34.5 GB VRAM. AMD Instinct MI210 64GB has 64.0 GB. With Q4_K_M quantization, expect ~142 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
141.5 tok/s
TTFT
1368 ms
Safe context
131K
Memory
34.5 GB / 64.0 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 | 141.5 tok/s | 746 ms | 131K |
| Coding | S | Runs well | 141.5 tok/s | 1368 ms | 131K |
| Agentic Coding | S | Runs well | 141.5 tok/s | 1989 ms | 131K |
| Reasoning | S | Runs well | 141.5 tok/s | 1616 ms | 131K |
| RAG | S | Runs well | 141.5 tok/s | 2487 ms | 131K |
How Qwen 3.6 35B A3B (35B params) fits at each quantization level on AMD Instinct MI210 64GB (64.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 13.7 GB | Low | A84 |
Q3_K_S | 3 | 17.2 GB | Low | S85 |
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 99Yes, AMD Instinct MI210 64GB can run Qwen 3.6 35B A3B with a S grade (Runs well). Expected decode speed: 141.5 tok/s.
Qwen 3.6 35B A3B (35B parameters) requires approximately 34.5 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 MI210 64GB, Qwen 3.6 35B A3B achieves approximately 141.5 tokens per second decode speed with a time-to-first-token of 1368ms using Q4_K_M quantization.
For coding workloads, Qwen 3.6 35B A3B on AMD Instinct MI210 64GB receives a S grade with 141.5 tok/s and 131K context.
On AMD Instinct MI210 64GB, Qwen 3.6 35B A3B can safely use up to 131K 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-mi210-64gb" 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 |
| S86 |
Q4_K_M | 4 | 21.3 GB | Medium | S86 |
Q5_K_M | 5 | 25.2 GB | High | S87 |
Q6_K | 6 | 28.7 GB | High | S88 |
Q8_0Best for your GPU | 8 | 37.5 GB | Very High | S90 |
F16 | 16 | 71.8 GB | Maximum | F0 |