DeepSeek-V4.1-Flash-1017 EXL3 on 2x DGX Sparks with TensorFold
7 daysStars46224h gain+7Score7.0
Search
Find trending repositories by name or description.
6 results for “exl3”
RankRepository7 daysStars24h gainScore
Sushi engine runs very high quality quant model in Apple Silicon, using both STQ and EXL3 format with special tuning technology.
7 daysStars44424h gain+4Score1.7
Pinned Intel Arc Pro B60/B70 inference recipes, engine patches and measurement records: Qwen3.8-27B EXL3 on one card (262,144 context, 63 tok/s; MTP3 measured lossy on 27% of a fixed 329-item set), Nemotron Bolt 74B, Flash-Next, dual-card routes, and a machine-checked catalog where each speculative row states whether the drafter changes the answer.
7 daysStars19524h gain0Score0.0
GLM-5.3 Flash EXL3 for 2-4x DGX Sparks
7 daysStars73524h gain-Score0.0
GLM-5.3-Flash EXL3 on 2x DGX Spark with TensorFold
7 daysStars50024h gain-Score0.0
GLM-5.3-Flash EXL3 on one 24 GB RTX 3090 + DDR4: elastic GPU expert cache, zero-copy experts, AVX2 CPU tier, OpenAI API
7 daysStars19724h gain-Score0.0