SYLIN

Qwen3.8-27B GGUF (ggml-org)

by ggml · Model · Language & code models

ggml-org GGUF build of Qwen3.8-27B runs locally in LM Studio, Ollama and llama.cpp; reviewer picks it for speed/quality balance

AccessOpen weightsNeeds~31 GBDownload20 GBLicenseApache 2.0

Evidence

  1. Aug 15
    Vision test at Q4_K_M: reconstructed occluded text on an Indonesian pempek stall sign and identified the cuisine correctly; thinking was longer than full precision

Cost to run

Alternatives

Made from