← AI Hashrate

Can RX 7700 XT 12GB run Qwen2.5-Coder-14B-Instruct?

AMD · 12 GB GDDR6 · 432 GB/s bandwidth · Alibaba · 14.8B · model ctx up to 32K

Partly — Qwen2.5-Coder-14B-Instruct at Q4 fits the RX 7700 XT 12GB (12 GB GDDR6) at 4K context (≈ 10.62 GB) but not at the default 8K (≈ 12.1 GB needed). Use a shorter context or partial offload. Decode at Q4/8K: ≈ 52.2 tok/s (estimated, batch 1). FP16 needs ≈ 33.56 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)
Q44K10.62 GBYes18.6 est.
Q48K default12.1 GBNo52.2 est.
Q432K20.98 GBNo17.4 est.
FP164K32.08 GBNo2.0 est.
FP168K default33.56 GBNo1.9 est.
FP1632K42.44 GBNo1.2 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 7700 XT 12GB VRAM
Q48.14 GB2.96 GB1 GB12.1 GB12 GB
FP1629.6 GB2.96 GB1 GB33.56 GB12 GB

Other GPUs that run Qwen2.5-Coder-14B-Instruct

All GPUs for Qwen2.5-Coder-14B-Instruct →

Other models for the RX 7700 XT 12GB

All models on the RX 7700 XT 12GB →