1× RTX 5090
252tok/sEveryday
1 request, prose prompt, no speculative decoding Source
Intelligence18with thinkingno thinking 15
Local AI · Creator
noonghunna
28 published recipes.
Recipes
2× RTX 5090
249tok/sEveryday
1 request, prose prompt, no speculative decoding Source
Intelligence18with thinkingno thinking 15
- License unclear
2× RTX 5090
218tok/sEveryday
1 request, prose prompt, no speculative decoding Source
Intelligenceno independent value
2× RTX 3090
179tok/sEveryday
1 request, prose prompt, no speculative decoding Source
Intelligence18with thinkingno thinking 15
- License unclear
1× RTX 3090
168tok/sEveryday
1 request, prose prompt, with MTP (per recipe) Source
Intelligence17with thinkingno thinking 13
2× RTX 5090
168tok/sEveryday
1 request, prose prompt, with MTP Source
Intelligence21with thinkingno thinking 20
2× RTX 5090
153tok/sEveryday
1 request, prose prompt, with MTP (per recipe) Source
Intelligence21with thinkingno thinking 20
2× RTX 3090
151tok/sEveryday
1 request, prose prompt, no speculative decoding Source
Intelligenceno independent value
2× RTX 5090
149tok/sEveryday
1 request, prose prompt, no speculative decoding Source
Intelligenceno independent value
- Experimental
- License unclear
4× RTX 3090
145tok/sEveryday
1 request, prose prompt, with DFlash (per recipe) Source
Intelligence34with thinkingno thinking 20
- Experimental
2× RTX 3090
144tok/sEveryday
1 request, prose prompt, no speculative decoding Source
Intelligenceno independent value
1× RTX 5090
128tok/sEveryday
1 request, prose prompt, with MTP (per recipe) Source
Intelligence21with thinkingno thinking 20
2× RTX 3090
123tok/sEveryday
1 request, prose prompt, with Draft Source
Intelligence34with thinkingno thinking 20
1× RTX 3090
113tok/sEveryday
1 request, prose prompt, with MTP (per recipe) Source
Intelligence18with thinkingno thinking 15
2× RTX 3090
109tok/sEveryday
1 request, prose prompt, with MTP (per recipe) Source
Intelligence21with thinkingno thinking 20
2× RTX 3090Qwen3.8-27B (ThinkingCap-Finetune)
108tok/sEveryday
1 request, prose prompt, with DFlash2 (per recipe) Source
Intelligenceno independent value
- Experimental
- Custom kernel required
- License unclear
4× RTX 3090
105tok/sEveryday
1 request, prose prompt, with MTP (per recipe) Source
Intelligence21with thinkingno thinking 20
4× RTX 3090
104tok/sEveryday
1 request, prose prompt, with MTP (per recipe) Source
Intelligenceno independent value
- Experimental
- License unclear
2× RTX 3090
76.4tok/sEveryday
1 request, prose prompt, with MTP Source
Intelligence34with thinkingno thinking 20
2× RTX 3090Qwen3.8-27B (ThinkingCap-Finetune)
74tok/sEveryday
1 request, prose prompt, with Draft Source
Intelligenceno independent value
- Experimental
- License unclear
2× RTX 3090
69.8tok/sEveryday
1 request, prose prompt, with MTP (per recipe) Source
Intelligence21with thinkingno thinking 20
1× RTX 3090
59.7tok/sEveryday
1 request, prose prompt, with MTP (per recipe) Source
Intelligence21with thinkingno thinking 20
1× RTX 3090
50.3tok/sEveryday
1 request, prose prompt, with MTP (per recipe) Source
Intelligence21with thinkingno thinking 20
2× RTX 3090
45.8tok/sEveryday
1 request, prose prompt, no speculative decoding Source
Intelligenceno independent value
- Experimental
- License unclear
1× RTX 3090
44.9tok/sEveryday
1 request, prose prompt, with DFlash (per recipe) Source
Intelligence19with thinkingno thinking 14
2× RTX 3090
36.8tok/sEveryday
1 request, prose prompt, with ngram Source
Intelligence40with thinking
- Partly in system RAM
- Experimental
- License unclear
2× RTX 3090
21.9tok/sEveryday
1 request, prose prompt, no speculative decoding Source
Intelligence34with thinking
- Partly in system RAM
- Experimental
2× RTX 3090
18.1tok/sEveryday
1 request, prose prompt, no speculative decoding Source
Intelligence42with thinking
- ≤ 3 bit: quantization may cost quality
- Partly in system RAM