Yes — with 56.2 GB to spare

Qwen3 235B-A22B at Q4_K_M fits your Instinct MI300X entirely on the GPU at 8K context, at an estimated 100 tokens per second. There is room for its full 128K window.

Fully on GPU 8K context Q4_K_M · 132.1 GB Apache 2.0 Released Apr 2025

Workstation class. Realistically a 192 GB unified-memory or multi-GPU model.

What hardware do I need for Qwen3 235B-A22B? →

The VRAM budget

weights 132.1 GB
Weights 132.1 GB KV cache @ 8K 1.47 GB Runtime overhead 0.6 GB Free 56.2 GB of 190.4 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
Q8_0 232.5 GB 234.6 GB ~3.2 −0.1% ppl 44.2 GB over
Q6_K 179.5 GB 181.5 GB 56K 73 −0.4% ppl Long context
Q5_K_M 155.1 GB 157.2 GB 128K 85 −0.8% ppl Long context
Q4_K_M 132.1 GB 134.2 GB 128K 100 −1.9% ppl Recommended
Q3_K_M 107.0 GB 109.0 GB 128K 123 −5.4% ppl Long context
Q2_K 91.6 GB 93.7 GB 128K 144 −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.

How to run it

terminal
$ ollama pull qwen3:235b-a22b
$ OLLAMA_CONTEXT_LENGTH=8192 \
    ollama run qwen3:235b-a22b

The default. One binary, a model registry, an OpenAI-compatible port. More on Ollama.

01Download is 132.1 GB. Keep it on an SSD — a first load off a spinning disk takes minutes.
02Close anything else holding VRAM. A browser with hardware acceleration can sit on 1–2 GB.
03There is room to go to the model's full 128K context on this card.
See all models for this rig Compare with another model