TP=3 just isn’t too worth for GB10’s imo.
Granted I haven’t made recipes, but gains are small. There are better mixes of models for 1x spark and 2x sparks and a big jump in performance to 4x. Recommendations: Single = Qwen3.6 35b-a3b Dual = Deepseek V4-FV Quad = Deepseek V4-FV
Give Deepseek Harness the speech plugin it deserves.
Dsh plugin --profile web add allmodels/dsh-speech
Deepseek pro 0813 is kinda good.
Promp : Draw a sitting cat tokens : 1254
Top-5 Best Value #LLM Models of the Day at UTC-04
| Model | #AAII | Price | | GLM 5.3 Flash | 58 | $0.09 | | DeepSeek V4 Flash 0731 | 52 | $0.06 | | Gemini 3.8 Flash | 59 | $0.57 | | Gemini 3.7 Flash | 56 | $0.57 | | GPT-5.6 Luna | 52 | $0.18 |
You have reached the end of the archive
All of deepseek