Can RX 7700 XT 12GB run DeepSeek-R1-Distill-Qwen-7B?
AMD · 12 GB GDDR6 · 432 GB/s bandwidth ·
DeepSeek · 7.6B · model ctx up to 128K
Yes — the RX 7700 XT 12GB (12 GB GDDR6) can run DeepSeek-R1-Distill-Qwen-7B. 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 12 GB. Decode at Q4/8K: ≈ 36.2 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
36.2est.
Q4
8K default
6.7 GB
Yes
36.2est.
Q4
32K
11.26 GB
Yes
36.2est.
FP16
4K
16.96 GB
No
14.2est.
FP16
8K default
17.72 GB
No
13.0est.
FP16
32K
22.28 GB
No
8.2est.
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).