1× RTX 5090
367tok/sPeak
1 request, synthetic prompt Source
Intelligence9with thinking
Local AI · Creator
notwitcheer
8 published recipes.
Recipes
1× RTX 5090
271tok/sPeak
1 request, synthetic prompt Source
Intelligence18with thinkingno thinking 15
1× RTX 5090
115tok/sPeak
1 request, synthetic prompt Source
Intelligence34with thinkingno thinking 20Original model's value. Heavily compressed (~2.1 bit), intelligence is likely much lower.
- ≤ 3 bit: quantization may cost quality
1× RTX 5090
61.9tok/sPeak
1 request, synthetic prompt Source
Intelligence21with thinkingno thinking 20
1× RTX 5090
59.7tok/sPeak
1 request, synthetic prompt Source
Intelligence40with thinking
- ≤ 3 bit: quantization may cost quality
- Partly in system RAM
- License unclear
1× RTX 5090
54.4tok/sPeak
1 request, synthetic prompt Source
Intelligence21with thinkingno thinking 20
1× RTX 5090
53tok/sPeak
1 request, synthetic prompt Source
Intelligence19with thinkingno thinking 14
1× RTX 5090
46.5tok/sPeak
1 request, synthetic prompt Source
Intelligence12with thinking
- Partly in system RAM