GLM-5.3-Flash-AWQ-W4A16-aggr-w8-mtpq8c-int4g32-mixA
Derived from wtdcode/GLM-5.3-Flash-AWQ-W4A16 @ abd7b07 (INT4 AWQ experts, compressed-tensors pack-quantized), itself a quantization of zai-org/GLM-5.3-Flash (MIT). This repo...
Derived from wtdcode/GLM-5.3-Flash-AWQ-W4A16 @ abd7b07 (INT4 AWQ experts, compressed-tensors pack-quantized), itself a quantization of zai-org/GLM-5.3-Flash (MIT). This repo...
5 October 2026 image, with the launcher of 6 October: ghcr.io/eliovp/paiton-vllm-plugin:qwen38-rocm10-vllm029-20261005-r1@sha256:245c71d54f046f89b74dbfbd4c894003754561e55c9d215a8d3ce65364fb0f80. One image serves the MXFP4 path and...
EXL3 pack of deepseek-ai/DeepSeek-V4.1-Flash. Routed experts are 2.0 bpw MCG. In the default revision they are re-encoded with...
— Model Architecture: GlmMoeDsaForCausalLM — Input: Text — Output: Text — Model Optimizations: — Weight quantization: FP4 —...
A sub-4-bit routed-expert quantization of Qwen/Qwen3.8-Flash-Next, built to fit the full 262,144-token context of a 125B-A6B multimodal MoE...
Текстовая квантизация Qwen/Qwen3.8-27B со смешанной точностью, созданная для соответствия строгому ограничению в 20 000 000 000 байт всего...
> Mirrors: canonical repo is on GitHub at > fattchris/qwen-dflash2-spark > (identical content). One-stop, copy-paste reproducible stack: run...
> [!IMPORTANT] > ~3.7× smaller than the original 16-bit Qwen3-4B, with 96.5% accuracy retention. 3-bit weight-only quantization for...
FP8 quantization of amalia-llm/AMALIA-9B-0626-DPO, the European Portuguese language model, for serving with vLLM. To the best of our...
> Work in progress. This card and the checkpoint are still being validated. Routed experts of DeepSeek-V4-Flash-0731 transcoded...