Qwen3.8-Flash-Next (GGUF Q8_0 + vision)

Alibaba / Qwen (GGUF: unsloth) · Qwen3.8
LLMQwen-Community-1.0publicTrusted177B params

llama.cpp GGUF build (Q8_0, Unsloth) of Qwen3.8-Flash-Next, a preview of the Qwen4 architecture: 177B MoE, 512 experts with 10 active, hybrid linear and sparse attention, 262144-token context. The manifest carries the F16 vision projector, so the entry reads images as well as text.

llama.cpp GGUF build (Q8_0, Unsloth) of Qwen3.8-Flash-Next, a preview of the Qwen4 architecture: 177B MoE, 512 experts with 10 active, hybrid linear and sparse attention, 262144-token context. The manifest carries the F16 vision projector, so the entry reads images as well as text.

At a glance

  • Task: LLM (InferenceV1)
  • Params: 177B
  • License: Qwen-Community-1.0
  • Hardware: 209 GB+ VRAM
  • dtype: Int8