GTX 1660 SUPER × Qwen3 Coder 0.6B 0.9B 7 1bR5 Nobs F16
Qwen3 Coder 0.6B 0.9B 7 1bR5 Nobs F16 on GTX 1660 SUPER
14.8best gen tok/s
317best prompt tok/s
640max context tested
1results
Measured · all numbers below come from the linked sources
llama.cpp
| Quant | Gen tok/s | Prompt tok/s | Source | Context tested | TTFT | Build |
|---|---|---|---|---|---|---|
| F16 | 14.8 | 317 | LocalScore ↗ | 512+128 | 4,438 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.