Yes — with 5.7 GB to spare

Qwen3.6 27B at Q4_K_M fits your Radeon RX 7900 XTX entirely on the GPU at 8K context, at an estimated 37 tokens per second. Past 98K 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 · 15.6 GB Apache 2.0 Released 22 Apr 2026 Vision

The 24 GB coding pick of spring 2026 (77.2 SWE-bench Verified). Same shape as 3.8, one generation behind.

What hardware do I need for Qwen3.6 27B? →

The VRAM budget

weights 15.6 GB

Weights 15.6 GB KV cache @ 8K 0.50 GB Runtime overhead 0.6 GB Free 5.7 GB of 22.4 GB

Quantisation ladder

Quant	Weights	Total @ 8K	Max context	Tok/s	Quality	Fit
Q8_0	27.5 GB	28.6 GB	—	~4.8	−0.1% ppl	6.2 GB over
Q6_K	21.2 GB	22.3 GB	9K	27	−0.4% ppl	Fits
Q5_K_M	18.4 GB	19.5 GB	55K	32	−0.8% ppl	Long context
Q4_K_M	15.6 GB	16.7 GB	98K	37	−1.9% ppl	Recommended
Q3_K_M	12.7 GB	13.8 GB	146K	46	−5.4% ppl	Long context
Q2_K	10.8 GB	11.9 GB	175K	54	−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 16 of its 64 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 llama.cpp LM Studio vLLM

terminal

$ ollama pull qwen3.6:27b
$ OLLAMA_CONTEXT_LENGTH=8192 \
    ollama run qwen3.6:27b

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

01Download is 15.6 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 98K context on this card.

See all models for this rig Compare with another model