1× RTX 3090
42.8tok/sEveryday
1 request, prose prompt, no speculative decoding Source
Intelligence34with thinkingno thinking 20
Local AI · Creator
r0b0tlab
41 published recipes.
Recipes
2× DGX Spark
32.5tok/sEveryday
1 request, prose prompt, with DSpark (adaptive verification) (per recipe) Source
Intelligenceno independent value
- Experimental
- Custom kernel required
1× DGX Spark
26.4tok/sEveryday
1 request, prose prompt, with MTP (NEXTN) (per recipe) Source
Intelligence40with thinking
- Custom kernel required
- License unclear
1× DGX Spark
19.5tok/sEveryday
1 request, prose prompt, with DFlash2 (per recipe) Source
Intelligence42with thinkingOriginal model's value. Heavily compressed (~2.3 bit), intelligence is likely much lower.
- ≤ 3 bit: quantization may cost quality
- Experimental
- Custom kernel required
- Non-commercial
2× DGX Spark
17.9tok/sEveryday
1 request, prose prompt, with DFlash2 Source
Intelligence42with thinking
- Custom kernel required
- Non-commercial
1× DGX Spark
99.5tok/sMixed
1 request, mixed prompt set, with MTP (per recipe) Source
Intelligence13with thinking
- License unclear
1× DGX Spark
93.1tok/sMixed
1 request, mixed prompt set, with MTP (per recipe) Source
Intelligence18with thinkingno thinking 15
2× DGX Spark
86.9tok/sMixed
1 request, mixed prompt set, with DSpark (per recipe) Source
Intelligence34with thinking
- Custom kernel required
1× DGX Spark
82.2tok/sMixed
1 request, mixed prompt set, with MTP (EAGLE/nextn) (per recipe) Source
Intelligenceno independent value
1× DGX Spark
79.7tok/sMixed
1 request, mixed prompt set, with MTP (per recipe) Source
Intelligence18with thinkingno thinking 15
1× DGX Spark
66.7tok/sMixed
1 request, mixed prompt set, with DFlash Source
Intelligence13with thinking
- License unclear
1× DGX Spark
64.6tok/sMixed
1 request, mixed prompt set, no speculative decoding Source
Intelligenceno independent value
2× DGX Spark
62.1tok/sMixed
1 request, mixed prompt set, with MTP (NEXTN) (per recipe) Source
Intelligence40with thinking
- License unclear
1× DGX Spark
57.5tok/sMixed
1 request, mixed prompt set, with MTP Source
Intelligence18with thinkingno thinking 15
1× DGX Spark
45.4tok/sMixed
1 request, mixed prompt set, no speculative decoding Source
Intelligence18with thinkingno thinking 15
1× DGX Spark
43.8tok/sMixed
1 request, mixed prompt set, no speculative decoding Source
Intelligenceno independent value
1× DGX Spark
43.5tok/sMixed
1 request, mixed prompt set, no speculative decoding Source
Intelligence25with thinking
- Custom kernel required
1× RTX 3090
38.6tok/sMixed
1 request, mixed prompt set, with MTP Source
Intelligence40with thinking
- ≤ 3 bit: quantization may cost quality
- Partly in system RAM
- License unclear
2× DGX Spark
36.1tok/sMixed
1 request, mixed prompt set, with MTP (per recipe) Source
Intelligence24with thinkingno thinking 19
- Experimental
- Custom kernel required
1× DGX SparkNex-N2-mini (Qwen3.5-MoE)
33.4tok/sMixed
1 request, mixed prompt set, no speculative decoding Source
Intelligenceno independent value
1× DGX Spark
29.6tok/sMixed
1 request, mixed prompt set, no speculative decoding Source
Intelligence17with thinkingno thinking 13
1× RTX 3090
27.8tok/sMixed
1 request, mixed prompt set, context 150000, with DFlash2 (per recipe) Source
Intelligence34with thinkingno thinking 20
- Custom kernel required
1× DGX Spark
27.8tok/sMixed
1 request, mixed prompt set, with MTP Source
Intelligence34with thinkingno thinking 20
- License unclear
1× DGX Spark
26.6tok/sMixed
1 request, mixed prompt set, with MTP Source
Intelligence21with thinkingno thinking 20
2× DGX Spark
24.1tok/sMixed
1 request, mixed prompt set, no speculative decoding Source
Intelligence23with thinking
- Custom kernel required
- License unclear
1× DGX Spark
23.5tok/sMixed
1 request, mixed prompt set, with DFlash2 (per recipe) Source
Intelligence34with thinkingno thinking 20
- Custom kernel required
- License unclear
1× DGX Spark
21.4tok/sMixed
1 request, mixed prompt set, with MTP (per recipe) Source
Intelligence25with thinking
- Custom kernel required
1× DGX Spark
20.6tok/sMixed
1 request, mixed prompt set, with DFlash (per recipe) Source
Intelligenceno independent value
- Custom kernel required
- License unclear
1× DGX SparkAgents-A1 (Qwen3.5-MoE)
17.5tok/sMixed
1 request, mixed prompt set, no speculative decoding Source
Intelligenceno independent value
- Experimental
1× DGX Spark
14.8tok/sMixed
1 request, mixed prompt set, with MTP Source
Intelligence13with thinking
- License unclear
2× DGX Spark
13.2tok/sMixed
1 request, mixed prompt set, no speculative decoding Source
Intelligence20with thinking
2× DGX Spark
11.4tok/sMixed
1 request, mixed prompt set, no speculative decoding Source
Intelligenceno independent value
- Custom kernel required
4× DGX Spark
11.2tok/sMixed
1 request, mixed prompt set, with DSpark (per recipe) Source
Intelligence40with thinkingno thinking 25
- Custom kernel required
1× DGX Spark
10.3tok/sMixed
1 request, mixed prompt set, no speculative decoding Source
Intelligence18with thinking
- Experimental
- Custom kernel required
2× DGX Spark
8.73tok/sMixed
1 request, mixed prompt set, no speculative decoding Source
Intelligenceno independent value
- Custom kernel required
- License unclear
1× DGX Spark
6.88tok/sMixed
1 request, mixed prompt set, no speculative decoding Source
Intelligence19with thinkingno thinking 14
- License unclear
1× DGX Spark
146tok/sPeak
1 request, mixed prompt set Source
Intelligence10with thinking
- Experimental
1× DGX Spark
71.3tok/sPeak
1 request, synthetic prompt, context 2048 Source
Intelligenceno independent value
1× DGX SparkFastContext-1.0 (Qwen3-4B)
66.3tok/sPeak
1 request, mixed prompt set Source
Intelligenceno independent value
- broken
2× DGX Spark
16tok/sPeak
1 request, mixed prompt set Source
Intelligence28with thinking
2× DGX Spark
no documented speed
Intelligenceno independent value
- Custom kernel required