RTX 2080 Ti × Qwen2.5 Coder 14B Instruct AWQ
Qwen2.5 Coder 14B Instruct AWQ on RTX 2080 Ti
37.9best gen tok/s
1,254best prompt tok/s
640max context tested
3results
Measured · all numbers below come from the linked sources
llama.cpp
| Quant | Gen tok/s | Prompt tok/s | Source | Context tested | TTFT | Build |
|---|---|---|---|---|---|---|
| Q4_0 | 37.9 | 1,254 | LocalScore ↗ | 512+128 | 994 ms | llamafile 0.9.2 |
| Q4_K - Medium | 35.9 | 1,133 | LocalScore ↗ | 512+128 | 1,104 ms | llamafile 0.9.2 |
| Q8_0 | 2.2 | 137 | LocalScore ↗ | 512+128 | 12,349 ms | llamafile 0.9.2 |
Ollama
No measured Ollama results yet. Submit yours →
MLX
No measured MLX results yet. Submit yours →
"Context tested" is the largest prompt+generation length actually benchmarked (tokens), not a memory-fit estimate.
What else can RTX 2080 Ti run? →
Includes results from LocalScore, a Mozilla Builders project by cjpais, mirrored in the cn0303/local-llm-speed-benchmarks dataset. LocalScore runs use llamafile, which is built on llama.cpp.