Yes — with 41.5 GB to spare
Qwen3.6 35B-A3B at Q4_K_M fits your Instinct MI210 entirely on the GPU at 8K context, at an estimated 206 tokens per second. There is room for its full 256K window.
Mixture of experts with ~3B active: the fastest serious model a 24 GB card runs, and the best MoE under 40B on agentic coding.
Hardware requirements What hardware do I need to run Qwen3.6 35B-A3B? →At Q4_K_M with an 8K context: a 32 GB GPU (RTX 5090) or a 36 GB Mac (M4 Max). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.
The VRAM budget
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| Q8_0 | 35.5 GB | 36.3 GB | 256K | 117 | −0.1% ppl | Long context |
| Q6_K | 27.4 GB | 28.2 GB | 256K | 151 | −0.4% ppl | Long context |
| Q5_K_M | 23.7 GB | 24.5 GB | 256K | 175 | −0.8% ppl | Long context |
| Q4_K_M | 20.2 GB | 20.9 GB | 256K | 206 | −1.9% ppl | Recommended |
| Q3_K_M | 16.3 GB | 17.1 GB | 256K | 254 | −5.4% ppl | Long context |
| Q2_K | 14.0 GB | 14.8 GB | 256K | 296 | −15% ppl | Long context |
Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it. Only 10 of its 40 blocks keep a per-token KV cache; the rest are linear-attention, Mamba or convolution blocks with a fixed-size state.
How to run it
$ ollama pull qwen3.6:35b-a3b $ OLLAMA_CONTEXT_LENGTH=8192 \ ollama run qwen3.6:35b-a3b
The default. One binary, a model registry, an OpenAI-compatible port. More on Ollama.
Related models on an Instinct MI210
| Model | Total | Tok/s est. | |
|---|---|---|---|
| Qwen3.6 27B 27.8B · same family |
Q4_K_M · 16.7 GB | 63 | Runs great |
| Ornith 1.5 35B-A3B 35.9B MoE · similar size |
Q4_K_M · 20.9 GB | 206 | Runs great |
| LLM-jp 4 33B Thinking 33.2B · similar size |
Q4_K_M · 21.3 GB | 53 | Runs great |
| Qwen3 32B 32.8B · similar size |
Q4_K_M · 21.0 GB | 54 | Runs great |
| DeepSeek-R1-Distill-Qwen 32B 32.8B · similar size |
Q4_K_M · 21.0 GB | 54 | Runs great |
| Qwen2.5-Coder 32B 32.8B · similar size |
Q4_K_M · 21.0 GB | 54 | Runs great |
| Olmo 3.1 32B Instruct 32.2B · similar size |
Q4_K_M · 20.0 GB | 55 | Runs great |
Qwen3.6 35B-A3B on other hardware
| Device | Total | Tok/s est. | |
|---|---|---|---|
| GeForce RTX 4060 Laptop 7.0 GB usable · 256 GB/s |
20.9 GB | — | Won't fit |
| GeForce RTX 3060 12 GB 10.6 GB usable · 360 GB/s |
20.9 GB | ~13 | CPU offload |
| M4 · 16 GB 10.7 GB usable · 120 GB/s |
20.9 GB | — | Won't fit |
| GeForce RTX 4090 22.4 GB usable · 1008 GB/s |
20.9 GB | 126 | Tight fit |
| Radeon RX 7900 XTX 22.4 GB usable · 960 GB/s |
20.9 GB | 120 | Tight fit |
| GeForce RTX 5090 30.4 GB usable · 1792 GB/s |
20.9 GB | 225 | Runs great |
| M4 Max · 36 GB 27.0 GB usable · 410 GB/s |
20.9 GB | 58 | Runs great |
| M3 Max · 64 GB 48.0 GB usable · 400 GB/s |
20.9 GB | 56 | Runs great |