RTX 4070 Ti × Mistral Nemo 2407 12B Thinking Claude Gemini GPT5.2 Uncensored HERETIC
Mistral Nemo 2407 12B Thinking Claude Gemini GPT5.2 Uncensored HERETIC on RTX 4070 Ti
13.6best gen tok/s
1,537best prompt tok/s
4,352max 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 |
|---|---|---|---|---|---|---|
| Q6_K | 13.6 | 1,537 | LocalScore ↗ | 4,352 | 813 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 RTX 4070 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.