2× RTX 3090
187tok/sEveryday
1 request, prose prompt, prompt 450 tokens, no speculative decoding Source
Intelligenceno independent value
Local AI · Creator
tonyd2wild
39 published recipes.
Recipes
4× RTX 3090
110tok/sEveryday
1 request, prose prompt, with MTP (per recipe) Source
Intelligence40with thinking
- License unclear
4× RTX 3090
85.3tok/sEveryday
1 request, prose prompt, with DFlash2 (per recipe) Source
Intelligence34with thinkingno thinking 20
2× DGX Spark
33.2tok/sEveryday
1 request, prose prompt, with DSpark (per recipe) Source
Intelligenceno independent value
- Custom kernel required
4× DGX Spark
31.5tok/sEveryday
1 request, prose prompt, with DFlash2 (per recipe) Source
Intelligence42with thinking
- Custom kernel required
- Non-commercial
4× DGX Spark
24.4tok/sEveryday
1 request, prose prompt, with DSpark (per recipe) Source
Intelligence40with thinkingno thinking 25
- Experimental
- Custom kernel required
2× DGX Spark
19.1tok/sEveryday
1 request, prose prompt, with DFlash2 (per recipe) Source
Intelligence42with thinking
- Non-commercial
- License unclear
2× DGX Spark
53.3tok/sMixed
1 request, mixed prompt set, with DFlash (per recipe) Source
Intelligenceno independent value
- Custom kernel required
2× DGX Spark
45.3tok/sMixed
1 request, mixed prompt set, with DSpark (per recipe) Source
Intelligenceno independent value
- Experimental
1× DGX Spark
43.9tok/sMixed
1 request, mixed prompt set, with MTP (per recipe) Source
Intelligence40with thinking
- Custom kernel required
- License unclear
2× DGX Spark
33tok/sMixed
1 request, mixed prompt set, with MTP (per recipe) Source
Intelligence28with thinking
- No license
4× DGX Spark
23.7tok/sMixed
1 request, mixed prompt set, with MTP (per recipe) Source
Intelligence34with thinkingno thinking 22
- Experimental
- Custom kernel required
4× RTX 3090
283tok/sPeak
1 request, code prompt Source
Intelligenceno independent value
- License unclear
4× DGX Spark
129tok/sPeak
1 request, synthetic prompt Source
Intelligenceno independent value
- Experimental
2× RTX 3090
101tok/sPeak
1 request, best value reported by source Source
Intelligence34with thinkingno thinking 20
2× DGX Spark
62.9tok/sPeak
1 request, JSON prompt Source
Intelligence25with thinking
2× DGX Spark
62.5tok/sPeak
1 request, best value reported by source Source
Intelligenceno independent value
4× DGX Spark
53.3tok/sPeak
1 request, JSON prompt Source
Intelligence45with thinking
- Custom kernel required
- License unclear
2× DGX Spark
46.9tok/sPeak
1 request, code prompt Source
Intelligence42with thinking
- Custom kernel required
- Access on request
- Non-commercial
2× DGX Spark
45.5tok/sPeak
1 request, best value reported by source, context 1m Source
Intelligence24with thinkingno thinking 19
- Custom kernel required
2× DGX Spark
45.1tok/sPeak
1 request, code prompt Source
Intelligence24with thinkingno thinking 19
4× RTX 3090
43tok/sPeak
1 request, best value reported by source Source
Intelligence40with thinking
- ≤ 3 bit: quantization may cost quality
- License unclear
2× DGX Spark
41tok/sPeak
1 request, best value reported by source Source
Intelligence24with thinkingno thinking 19
- Deprecated
2× DGX Spark
40tok/sPeak
1 request, best value reported by source Source
Intelligence24with thinkingno thinking 19
3× DGX Spark
38.8tok/sPeak
1 request, best value reported by source Source
Intelligence25with thinking
- Superseded
2× DGX Spark
38.3tok/sPeak
1 request, mixed prompt set, context 160k Source
Intelligence25with thinking
- Experimental
- Custom kernel required
- Superseded
3× DGX Spark
38.2tok/sPeak
1 request, mixed prompt set Source
Intelligence25with thinking
- Experimental
- Custom kernel required
4× DGX Spark
38tok/sPeak
1 request, best value reported by source Source
Intelligence29with thinking
- License unclear
2× DGX Spark
37.8tok/sPeak
1 request, JSON prompt Source
Intelligence25with thinking
- Custom kernel required
2× DGX Spark
36.6tok/sPeak
1 request, JSON prompt, context 196k Source
Intelligence29with thinking
- License unclear
4× DGX Spark
33.7tok/sPeak
1 request, best value reported by source Source
Intelligence29with thinking
- Experimental
- Custom kernel required
- License unclear
4× DGX Spark
32.5tok/sPeak
1 request, best value reported by source Source
Intelligence34with thinkingno thinking 22
2× DGX Spark
31.9tok/sPeak
1 request, best value reported by source Source
Intelligence25with thinking
- Custom kernel required
4× DGX Spark
23tok/sPeak
1 request, best value reported by source Source
Intelligence34with thinkingno thinking 22
2× DGX Spark
21.8tok/sPeak
1 request, best value reported by source Source
Intelligenceno independent value
2× DGX Spark
21.5tok/sPeak
1 request, best value reported by source, context 32k Source
Intelligenceno independent value
- ≤ 3 bit: quantization may cost quality
- Experimental
3× DGX Spark
10.5tok/sPeak
1 request, best value reported by source Source
Intelligence29with thinking
- License unclear
4× DGX Spark
no documented speed
Intelligence34with thinkingno thinking 22
- ≤ 3 bit: quantization may cost quality
- Custom kernel required
2× DGX Spark
no documented speed
Intelligence28with thinking
- Experimental
- License unclear