llama.cpp on the NVIDIA RTX 3080 20GB
On the NVIDIA RTX 3080 20GB, llama.cpp runs Qwen3.8 27B at 4-bit at a median 31.3 tokens per second for generation, from 1 plain run (96K context).
Speed by model on the NVIDIA RTX 3080 20GB
Plain runs only: one device, one request, no speculative decoding, the whole model in memory. Each row is one model size at one bit class, with the other engines' plain runs of the same model on this card beside it. Context length and build still differ between runs, and each side shows its own.
| Model | llama.cpp | Other engines |
|---|---|---|
| Qwen3.8 27B 4-bit | 31.3 t/sone report, 96K context | no other engine reported |
3 llama.cpp reports on the NVIDIA RTX 3080 20GB
Newest first. A run on several cards, with speculative decoding, with part of the model in system RAM or with batched requests says so, since each describes a different setup.
- Qwen3.8 27B · Q821.0 t/s(2 cards, speculative decoding)
- Qwen3.8 27B · Q4_K_XL31.3 t/s
- DeepSeek V4 Flash 284B · 13B active · IQ2XXS-w2Q2K-AProjQ8-SExpQ8-OutQ817.5 t/s(2 cards, part in system RAM)
Frequently asked
How fast is llama.cpp on the NVIDIA RTX 3080 20GB?
On the NVIDIA RTX 3080 20GB, llama.cpp runs Qwen3.8 27B at 4-bit at a median 31.3 tokens per second for generation, from 1 plain run (96K context).