An **NVFP4 (4-bit) Qwen3-VL-32B text encoder** for MiniMax-H3, made with `convert-to-quant`. It is a drop-in replacement for the H3 conditioning text encoder (ComfyUI `CLIPLoader`, type `minimax`). The H3 video weights are unchanged — only the text encoder is quantized to 4-bit, to bring the full H3 stack onto consumer GPUs. This encoder deliberately keeps more of the network in bf16 than a minimum-size 4-bit encoder does. The `--qwen_vlm` filter protects — at bf16 — the token embeddings, the **first and last language layers**, and the **entire vision tower**, quantizing only the middle language-layer linears to NVFP4. The result is 16.64 GiB, about 2 GiB above the most aggressively quantized community NVFP4 encoders (≈14.6 GiB, e.g. the AWQ-quantized encoder in `Comfy-Org/MiniMax-H3`), in exchange for leaving the precision-sensitive layers (embeddings, boundary layers, vision) untouched. It is a fidelity-first tradeoff: spend ~2 GiB more VRAM to keep the layers that most affect conditioning at full precision. Everything still fits a 24 GB card with offload. Everything is held constant except encoder precision — the bf16 encoder vs this NVFP4 encoder, same prompts, same seeds, same DiT — over a 16-clip paired set.

译文排队中 · 当前显示来源原文

视频生成

输入文本→ 输出视频

价格待核验多模态与渠道费用须分别核对

查看详情 ↗

加入对比来源 / 文档 ↗

Qwen3-14B-GGUF

6block

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

基础资料已收录 · 缺失资料后续补充

文本生成

输入文本→ 输出文本

价格待核验多模态与渠道费用须分别核对

查看详情 ↗

加入对比来源 / 文档 ↗

Qwen3-30B-A3B-GGUF

6block

All quants made using the imatrix option with a bilingual (English + Chinese) and code-heavy calibration dataset, so low-bit quants keep more of their Chinese and coding ability than a English-only calibration would. The `.imatrix` file used to produce these quants is included in this repo, so anyone can reproduce or extend the quant set with the exact same importance matrix. The first thing to figure out is how big a model you can run. For that you need to know how much RAM and/or VRAM you have.

译文排队中 · 当前显示来源原文

文本生成

输入文本→ 输出文本

价格待核验多模态与渠道费用须分别核对

查看详情 ↗

加入对比来源 / 文档 ↗

Qwen3-32B-GGUF

6block

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

基础资料已收录 · 缺失资料后续补充

文本生成

输入文本→ 输出文本

价格待核验多模态与渠道费用须分别核对

查看详情 ↗

加入对比来源 / 文档 ↗

Qwen3.8-27B-GGUF

6block

A 27B dense vision-language model (27.8B including the vision tower). 64 decoder layers in a hybrid stack: `full_attention_interval=4` means every fourth layer is grouped-query full attention (16 layers) and the rest are Gated DeltaNet linear attention (48 layers). Vocab 248320 with untied embeddings. Context length 262144 natively, extensible further with YaRN. The mmproj file is separate by design: llama.cpp loads the text backbone and the vision projector as two files. Download one tier plus one mmproj. Without the mmproj the model still runs, but text-only. The `mmproj-` and `mtp-` prefixes are what recent llama.cpp builds match on to tell the three file kinds apart, so `-hf 6block/Qwen3.8-27B-GGUF` picks a backbone rather than a projector, and `--spec-type mtp` finds the draft on its own.

译文排队中 · 当前显示来源原文

视觉问答

输入文本 · 图像→ 输出文本

价格待核验多模态与渠道费用须分别核对

查看详情 ↗

加入对比来源 / 文档 ↗