gdubicki/Qwen3-Coder-Next-NVFP4-GB10

Weights are byte-identical to the upstream quant (config.json and model.safetensors.index.json SHA-256 verified). This mirror exists to provide a pinned, stable, ungated reference for the qwen3-coder-next deployment project on DGX Spark (GB10). Use the upstream repo if you want to track author updates. — Base model: Qwen/Qwen3-Coder-Next by Alibaba / Qwen team (Apache-2.0) — NVFP4 quantization: saricles using LLM Compressor with LLMCOMPRESSORMOECALIBRATEALLEXPERTS=1 (all 512 experts calibrated) — Calibration data: HuggingFaceH4/ultrachat200k (64 samples × 2048 tok) — License: Apache-2.0** (inherited from base model; redistribution permitted) — Architecture: qwen3next — Hybrid DeltaNet linear attention + full attention + latent MoE — Layers: 48 total (36 DeltaNet linear-atte

Модальности:
Генерация текста

Области применения:
Генерация кода Диалог / чат

Задача: Генерация текста
Автор: gdubicki
Теги: qwen3_next, qwen3, nvfp4, 4-bit, quantized, compressed-tensors, vllm, DGX-Spark
Лайков: 3  |  Загрузок: 1,825

Открыть на HuggingFace →

Описание основано на материалах HuggingFace. Перевод выполнен автоматически.