Muse-Spark-Open-816B-A42B-INT4
This model is a W4A16 (int4, group_size 128, symmetric) model of meta-models/Muse-Spark-Open-816B-A42B generated by intel/auto-round using RTN. Please...
Метка: w4a16
Hemmingway-1-GPTQ-Int4-sym-G128-MTP-BF16
Unofficial 4-bit GPTQ quantization of Altworld/Hemmingway-1 for low-VRAM inference, with the MTP (multi-token-prediction) draft head deliberately kept unquantized....
DeepSeek-V4.1-Flash-W4A16-Engram-AutoRound
INVALID LANGUAGE PAIR SPECIFIED. EXAMPLE: LANGPAIR=EN|IT USING 2 LETTER ISO OR RFC3066 LIKE ZH-CN. ALMOST ALL LANGUAGES SUPPORTED...
Qwen3.8-27B-MTP-W4A16-VOLTA-Ampere
Квантование INT4 (W4A16) Qwen/Qwen3.8-27B построено специально для того, чтобы модель работала на графических процессорах Pre-Hopper, включая Volta (V100,...
DeepSeek-V4-Flash-0731-INT4-W4A16
> Work in progress. This card and the checkpoint are still being validated. Routed experts of DeepSeek-V4-Flash-0731 transcoded...
Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP-AutoRound-W4A16-Tuning
Эта модель представляет собой квантование только по массе int4 с group_size 128 и симметричным квантованием DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP, сгенерированным AutoRound....
Laguna-S-2.1-NVFP4-W4A16-Quality
Quality-first mixed-precision ModelOpt quantization of poolside/Laguna-S-2.1, exported directly from Poolside’s BF16 checkpoint. This is a serving-oriented checkpoint, not...
Qwythos-9B-v2-AWQ
AWQ (W4A16) quantization of empero-ai/Qwythos-9B-v2 — a 9.65B reasoning / uncensored model from Empero AI (qwen35`: dense hybrid...
ThinkingCap-Qwen3.6-27B-AutoRound-W4A16-Tuning
Эта модель представляет собой квантование только веса int4 с group_size 128 и симметричным квантованием bottlecapai/ThinkingCap-Qwen3.6-27B, сгенерированным НАСТРОЙКОЙ. Пожалуйста,...
Qwen3.5-4B-QAD-W4A16
We reduce Qwen3.5-4B inference latency on a single A10G by quantizing both the target model and its speculative-decoding...