1× Mac
155tok/sEveryday
1 request, llmprobe standard prompt, thinking on, with MTP + PLD (per recipe) Source
Intelligence40with thinking
- Experimental
- License unclear
Local AI · Creator
drowzeys
15 published recipes.
Recipes
1× Mac
35.8tok/sEveryday
1 request, llmprobe standard prompt, thinking on, with embedded MTP (2 draft tokens) (per recipe) Source
Intelligence42with thinking
- Experimental
- No license on HF
- License unclear
2× DGX Spark
31.6tok/sEveryday
1 request, prose prompt, with DSpark (per recipe) Source
Intelligence40with thinkingno thinking 25
- ≤ 3 bit: quantization may cost quality
- Custom kernel required
1× Mac
25.1tok/sEveryday
1 request, prose prompt, short prompt, with MTP (DSpark built-in) (per recipe) Source
Intelligence40with thinkingno thinking 25
- ≤ 3 bit: quantization may cost quality
- No license on HF
- License unclear
4× DGX Spark
24.2tok/sEveryday
1 request, prose prompt, with MTP k=2 (per recipe) Source
Intelligenceno independent value
- Custom kernel required
2× DGX Spark
19.4tok/sEveryday
1 request, essay prompt, with MTP (per recipe) Source
Intelligence25with thinking
- Restrictive license
- License unclear
2× DGX Spark
51tok/sPeak
1 request, best value reported by source Source
Intelligenceno independent value
- Access on request
2× DGX Spark
50tok/sPeak
1 request, best value reported by source Source
Intelligenceno independent value
2× DGX Spark
33tok/sPeak
1 request, best value reported by source, context 1m Source
Intelligence28with thinking
- Custom kernel required
- License unclear
1× DGX Spark
31.7tok/sPeak
1 request, best value reported by source Source
Intelligence34with thinkingno thinking 20
4× DGX Spark
28.8tok/sPeak
1 request, best value reported by source Source
Intelligence34with thinkingno thinking 22
1× DGX Spark
27.7tok/sPeak
1 request, best value reported by source Source
Intelligenceno independent value
- License unclear
2× DGX Spark
22.3tok/sPeak
1 request, best value reported by source Source
Intelligence25with thinking
- Restrictive license
- License unclear
4× DGX Spark
15.3tok/sPeak
1 request, best value reported by source Source
Intelligence34with thinkingno thinking 22
4× DGX Spark
14.1tok/sPeak
1 request, best value reported by source Source
Intelligence34with thinkingno thinking 22