AIが動く。未来が更新される。Qwen3.8-Flash-Next-GSQ-RCO-GGUF
**Non-uniform GGUF quantizations** of a 512-expert MoE, produced with **GSQ** and **RCO**, with a vision projector for multimodal use. This repository provides GGUF quantizations of **Qwen3.8-Flash-Next** at four sizes, together with the model's vision projector (`mmproj`) for multimodal use. In contrast to uniform quantization, which applies a single quantization type to all weight tensors, each model here assigns a separate quantization type to every tensor. The assignment is obtained by a gradient-based search that allocates precision according to per-tensor sensitivity, subject to a total size budget. The resulting files are standard GGUF and run unmodified in `llama.cpp`, Ollama, and LM Studio. A code-specialized variant is released separately as Qwen3.8-Flash-Next-GSQ-RCO-Coder, which retains 256 of the 512 routed experts per layer at an effective 1.89 bpw over the original parameters, for a 58.4 GB total.
翻訳準備中のため原文を表示しています
**Non-uniform GGUF quantizations** of a 512-expert MoE, produced with **GSQ** and **RCO**, with a vision projector for multimodal use. This repository provides GGUF quantizations of **Qwen3.8-Flash-Next** at four sizes, together with the model's vision projector (`mmproj`) for multimodal use. In contrast to uniform quantization, which applies a single quantization type to all weight tensors, each model here assigns a separate quantization type to every tensor. The assignment is obtained by a gradient-based search that allocates precision according to per-tensor sensitivity, subject to a total size budget. The resulting files are standard GGUF and run unmodified in `llama.cpp`, Ollama, and LM Studio. A code-specialized variant is released separately as Qwen3.8-Flash-Next-GSQ-RCO-Coder, which retains 256 of the 512 routed experts per layer at an effective 1.89 bpw over the original parameters, for a 58.4 GB total.