Can RX 9070 XT 16GB run Qwen2.5-Coder-7B-Instruct?
AMD · 16 GB GDDR6 · 640 GB/s bandwidth ·
Alibaba · 7.6B · model ctx up to 32K
Yes — the RX 9070 XT 16GB (16 GB GDDR6) can run Qwen2.5-Coder-7B-Instruct. At Q4 with the default 8K context it needs ≈ 6.7 GB VRAM (weights 4.18 GB + KV cache 1.52 GB + 1 GB runtime overhead), which fits within 16 GB. Decode at Q4/8K: ≈ 53.6 tok/s (estimated, batch 1). FP16 needs ≈ 17.72 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
Quant
Context
VRAM needed
Fits?
tok/s (decode)
Q4
4K
5.94 GB
Yes
53.6est.
Q4
8K default
6.7 GB
Yes
53.6est.
Q4
32K
11.26 GB
Yes
53.6est.
FP16
4K
16.96 GB
No
37.5est.
FP16
8K default
17.72 GB
No
34.3est.
FP16
32K
22.28 GB
No
21.7est.
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).