Can I run it?
Can I run Qwen3.6 27B on Radeon RX 9070 XT?
Tight fit
Tight fit fully on your Radeon RX 9070 XT at UD-Q3_K_XL, 4K context, about 24–33 tok/s. Weights 13.5 GB plus 0.32 GB of KV cache — 14.2 GB of 14.7 GB usable.
Best quantUD-Q3_K_XL
Working context4K
Max that fits4K
Speed24–33 tok/sEstimate from memory bandwidth, not a benchmark. Method.
Weights13.5 GB
KV cache0.32 GB
Total14.2 GB
Usable14.7 GB
Qwen3.6 27B details · Radeon RX 9070 XT page · How this estimate is made
Run commands
llama.cpp
llama-server -hf unsloth/Qwen3.6-27B-GGUF:UD-Q3_K_XL -c 4096 -ngl 64
Ollama
ollama run qwen3.6
LM Studio
lms get unsloth/Qwen3.6-27B-GGUF # Then load quant UD-Q3_K_XL
Assumptions
- Estimate from memory bandwidth, not a benchmark. Decode speed uses 55–75% of peak bandwidth.
- KV cache is FP16. Engine overhead assumes llama.cpp (0.3 GB + 1% of the weights). Ollama is closer to 0.9 GB + 3%, LM Studio closer to 1 GB + 3%.
- UD-Q3_K_XL size is the real GGUF file size from Hugging Face.
- 0.5 GB is reserved because this GPU also drives a display, then 5% of the rest is left free.
- Speed is quoted at 4K context, not at the maximum context that still fits.
Larger models that also fit
- Can I run Qwen3.8 27B on Radeon RX 9070 XT? — Tight fit, UD-IQ4_XS, 24–32 tok/s (estimate)
- Can I run Qwen3.6 35B A3B on Radeon RX 9070 XT? — Tight fit, UD-IQ3_S, 61–84 tok/s (estimate)
- Can I run Qwen3.8 35B A3B Distill on Radeon RX 9070 XT? — Tight fit, Q2_K, 61–83 tok/s (estimate)
Updated 2026-10-24. Profile on this page is the device default plus 32 GB of DDR5-5600 system RAM.