DeepSeek-V4-Flash-2bit-GB10
A 2-bit quantization of deepseek-ai/DeepSeek-V4-Flash (299 B params, MoE) that serves on a single NVIDIA DGX Spark (GB10,...
A 2-bit quantization of deepseek-ai/DeepSeek-V4-Flash (299 B params, MoE) that serves on a single NVIDIA DGX Spark (GB10,...
This is an experimental hybrid GLM-5.2 checkpoint for vLLM/B12X serving. — the dense, attention, shared-expert, special-head, and MTP...
This repo quantizes the model using a data-free quantization tool. This release is prepared for vLLM with compressed-tensors...
INT4 weight-only (W4A16) quantization of Qwen/Qwen3.6-35B-A3B — a hybrid Mixture-of-Experts model (256 experts, top-8, ~3B active) with GatedDeltaNet...
— Qwopus3.6-27B-v2-heretic-F16.gguf — Qwopus3.6-27B-v2-heretic-Q4KM.gguf For llama.cpp or llama-server, use Q4KM for normal inference. For vLLM, GGUF support is...
터미널 작업 자동화를 위한 Terminal SFT 모델입니다. 입력된 작업/이전 터미널 상태를 보고 다음에 실행할 명령을 JSON 형태로 생성하는...
터미널 작업 자동화를 위한 Terminal SFT 모델입니다. 입력된 작업/이전 터미널 상태를 보고 다음에 실행할 명령을 JSON 형태로 생성하는...
> 2026-05-03 Исправление конфигурации: ropescaling.mscalealldim в config.json был исправлен с 1,0 до 0,0, что соответствует исправлению Mistral выше...
Эта модель mlx-community/gpt-oss-120b-mxfp4-bf16 была преобразована в формат MLX из openai/gpt-oss-120b с использованием mlx-lm версии 0.31.3. Модальности:Генерация текста Области...
This is a PrismaQuant 4.75-bit mixed-native quantization of mistralai/Mistral-Medium-3.5-128B, exported for vLLM using the compressed-tensors format. This artifact...