← AI Hashrate

Can RX 7900 XT 20GB run Qwen3-0.6B?

AMD · 20 GB GDDR6 · 800 GB/s bandwidth · Alibaba · 0.8B · model ctx up to 40K

Yes — the RX 7900 XT 20GB (20 GB GDDR6) can run Qwen3-0.6B. At Q4 with the default 8K context it needs ≈ 1.6 GB VRAM (weights 0.44 GB + KV cache 0.16 GB + 1 GB runtime overhead), which fits within 20 GB. Decode at Q4/8K: ≈ 636.4 tok/s (estimated, batch 1). FP16 (≈ 2.76 GB) also fits, at ≈ 175.0 tok/s (estimated). 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)
Q44K1.52 GBYes636.4 est.
Q48K default1.6 GBYes636.4 est.
Q432K2.08 GBYes636.4 est.
FP164K2.68 GBYes175.0 est.
FP168K default2.76 GBYes175.0 est.
FP1632K3.24 GBYes175.0 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 XT 20GB VRAM
Q40.44 GB0.16 GB1 GB1.6 GB20 GB
FP161.6 GB0.16 GB1 GB2.76 GB20 GB

Other GPUs that run Qwen3-0.6B

All GPUs for Qwen3-0.6B →

Other models for the RX 7900 XT 20GB

All models on the RX 7900 XT 20GB →