DeepSeek-V4.1-Flash-1017-oQ4e-ngram-mtp
mlx-community · Kit
A mixed-precision MLX copy of DeepSeek-V4.1-Flash-1017 that keeps the Engram tables at FP8. Made for people with hundreds of GB of memory who want to run the m…
New
AI projects from Hugging Face
Categories and filters
Listings
Runs a pruned, 2-bit DeepSeek-V4.1-Flash on a 128 GB Mac through mlx-serve, keeping 192 of 384 experts and a 1M-token context. Strongest on code, reasoning and…
New
DeepSeek-V4.1-Flash-1017 TrellisMX K2 Mix
brandonmusic · Kit
A compressed copy of DeepSeek-V4.1-Flash-1017 sized for two 96 GB GPUs, with a few experts stored at higher precision. A research build for people who serve la…
New