← AI Hashrate

Can RX 7900 XTX 24GB run Qwen3.6-27B?

AMD · 24 GB GDDR6 · 960 GB/s bandwidth · Alibaba · 27.8B · model ctx up to 256K

Yes — the RX 7900 XTX 24GB (24 GB GDDR6) can run Qwen3.6-27B. At Q4 with the default 8K context it needs ≈ 21.85 GB VRAM (weights 15.29 GB + KV cache 5.56 GB + 1 GB runtime overhead), which fits within 24 GB. Decode at Q4/8K: ≈ 22.0 tok/s (estimated, batch 1). FP16 needs ≈ 62.16 GB — does not fit on this card. Estimates come from memory-bandwidth math; rows tagged measured override estimates. Relative ranking is more reliable than absolute tok/s. Methodology.

Fit & speed by quant and context

QuantContextVRAM neededFits?tok/s (decode)
Q44K19.07 GBYes22.0 est.
Q48K default21.85 GBYes22.0 est.
Q432K38.53 GBNo24.4 est.
FP164K59.38 GBNo2.8 est.
FP168K default62.16 GBNo2.6 est.
FP1632K78.84 GBNo1.6 est.

Fits = weights + KV(ctx) + 1 GB overhead ≤ 95% of VRAM. Measured anchors are context-agnostic; the fit verdict is recomputed per context. A missing tok/s means the model is far beyond this card (offload-only territory).

VRAM breakdown at 8K context

QuantWeightsKV cacheOverheadTotal neededRX 7900 XTX 24GB VRAM
Q415.29 GB5.56 GB1 GB21.85 GB24 GB
FP1655.6 GB5.56 GB1 GB62.16 GB24 GB

Other GPUs that run Qwen3.6-27B

All GPUs for Qwen3.6-27B →

Other models for the RX 7900 XTX 24GB

All models on the RX 7900 XTX 24GB →