GTX 1660 SUPER × Qwen2.5 0.5B Instruct
Qwen2.5 0.5B Instruct on GTX 1660 SUPER
63.9best gen tok/s
1,520best 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_K - Medium | 63.9 | 1,507 | LocalScore ↗ | 512+128 | 936 ms | llamafile 0.9.3 |
| Q4_K - Medium | 63.9 | 1,516 | LocalScore ↗ | 512+128 | 935 ms | llamafile 0.9.3 |
| Q4_K - Medium | 63.8 | 1,520 | LocalScore ↗ | 512+128 | 936 ms | llamafile 0.9.3 |
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 GTX 1660 SUPER 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.