Qwen3-4B-ORA-W3
> [!IMPORTANT] > ~3.7× smaller than the original 16-bit Qwen3-4B, with 96.5% accuracy retention. 3-bit weight-only quantization for...
> [!IMPORTANT] > ~3.7× smaller than the original 16-bit Qwen3-4B, with 96.5% accuracy retention. 3-bit weight-only quantization for...
> GGUF quantizations of AMD’s Instella-MoE-16B-A3B-Think, converted and optimized for local inference with llama.cpp-compatible runtimes that support the...
This is an uncensored version of deepseek-ai/DeepSeek-V4-Flash-0731 created with abliteration (see remove-refusals-with-transformers to know more about it). This...
This repository contains an EXL3 quantization of Qwen/Qwen3.8-27B for ExLlamaV3. — Model: Qwen/Qwen3.8-27B — Quantizer: exllamav3-1.4.1 — Format:...
FP8 quantization of amalia-llm/AMALIA-9B-0626-DPO, the European Portuguese language model, for serving with vLLM. To the best of our...
Derivative of Qwen3.8-27B, quantized using MagicQuant hybrid evolutionary per-tensor search. Sibling repo with AMD-native (ROCmFPX fork-only) builds: lmcoleman/Qwen3.8-27B-ROCmFPX-GGUF....
An NVFP4-quantized, text-only build of Qwen/Qwen3.8-27B: vision tower removed, MTP head grafted back in bf16 so vLLM speculative...
INVALID LANGUAGE PAIR SPECIFIED. EXAMPLE: LANGPAIR=EN|IT USING 2 LETTER ISO OR RFC3066 LIKE ZH-CN. ALMOST ALL LANGUAGES SUPPORTED...
Этот репозиторий содержит локальное квантование EXL3 Qwen/Qwen3.8-27B для ExLlamaV3. — Базовая модель: Qwen/Qwen3.8-27B — Формат: EXL3 — Битрейт...
Imatrix-guided, measured-allocation APEX quantizations of nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B — a Nemotron-H hybrid: 52 layers of which only 6 are full...