Yes — with 3.9 GB to spare

Qwen3 30B-A3B at Q4_K_M fits your Radeon RX 7900 XTX entirely on the GPU at 8K context, at an estimated 120 tokens per second. Past 49K the KV cache pushes it over — quantise the cache to q8_0, or step down a quantisation, to go longer.

Fully on GPU 8K context Q4_K_M · 17.1 GB Apache 2.0 Released Apr 2025

The MoE that made "3B active" a category. Qwen3.6 35B-A3B is its direct replacement.

What hardware do I need for Qwen3 30B-A3B? →

The VRAM budget

weights 17.1 GB

Weights 17.1 GB KV cache @ 8K 0.75 GB Runtime overhead 0.6 GB Free 3.9 GB of 22.4 GB

Quantisation ladder

Quant	Weights	Total @ 8K	Max context	Tok/s	Quality	Fit
Q8_0	30.2 GB	31.5 GB	—	~12	−0.1% ppl	9.1 GB over
Q6_K	23.3 GB	24.6 GB	—	~36	−0.4% ppl	2.2 GB over
Q5_K_M	20.1 GB	21.5 GB	17K	103	−0.8% ppl	Long context
Q4_K_M	17.1 GB	18.5 GB	49K	120	−1.9% ppl	Recommended
Q3_K_M	13.9 GB	15.2 GB	84K	149	−5.4% ppl	Long context
Q2_K	11.9 GB	13.2 GB	105K	174	−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

Ollama llama.cpp LM Studio vLLM

terminal

$ ollama pull qwen3:30b-a3b
$ OLLAMA_CONTEXT_LENGTH=8192 \
    ollama run qwen3:30b-a3b

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

01Download is 17.1 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 49K context on this card.

See all models for this rig Compare with another model