1× RTX 3090
57tok/sEveryday
1 request, prose prompt, with MTP Source
Intelligenceno independent value
- Custom kernel required
Local AI · Creator
alesha-pro
11 published recipes.
Recipes
1× RTX 3090
57tok/sEveryday
1 request, prose prompt, with MTP Source
Intelligenceno independent value
- Custom kernel required
1× RTX 3090
39.7tok/sEveryday
1 request, prose prompt, no speculative decoding Source
Intelligence34with thinkingno thinking 20
4× RTX 3090
87.5tok/sMixed
1 request, mixed prompt set, with Draft Source
Intelligenceno independent value
- Experimental
- License unclear
4× RTX 3090
76.7tok/sMixed
1 request, mixed prompt set, context 8k, with MTP Source
Intelligence34with thinkingno thinking 20
4× RTX 3090
39.3tok/sMixed
1 request, mixed prompt set, no speculative decoding Source
Intelligence34with thinking
- ≤ 3 bit: quantization may cost quality
- Experimental
- Custom kernel required
2× RTX 3090
65.3tok/sPeak
1 request, best value reported by source Source
Intelligenceno independent value
1× RTX 3090
63.9tok/sPeak
1 request, best value reported by source Source
Intelligenceno independent value
4× RTX 3090
38.9tok/sPeak
1 request, best value reported by source Source
Intelligenceno independent value
- ≤ 3 bit: quantization may cost quality
- Experimental
- Custom kernel required
2× RTX 3090
no documented speed
Intelligenceno independent value
- Experimental
4× RTX 3090
no documented speed
Intelligence40with thinking
- Experimental
- Custom kernel required
- License unclear