From 7d142ed59dde72d6f6997df765524fca475414a8 Mon Sep 17 00:00:00 2001 From: Haylan Date: Sat, 31 Oct 2026 17:01:27 +0100 Subject: [PATCH] fix(models): correct DFlash2 Q8_0 drafter download URL The URL used the filename as the Hugging Face repo name. Also align the compose fallback for LLAMA_DRAFT_MODEL_FILE with Q8_0. Co-Authored-By: Claude Opus 5.5 --- docker-compose.yml | 2 +- models.yml | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/docker-compose.yml b/docker-compose.yml index 8dd3ea4..90a0225 100644 --- a/docker-compose.yml +++ b/docker-compose.yml @@ -29,7 +29,7 @@ services: --cache-type-v q8_0 --cache-ram ${LLAMA_CACHE_RAM:-24576} --spec-type draft-dflash - -md /models/${LLAMA_DRAFT_MODEL_FILE:-Qwen3.8-27B-DFlash2-Q4_K_M.gguf} + -md /models/${LLAMA_DRAFT_MODEL_FILE:-Qwen3.8-27B-DFlash2-Q8_0.gguf} --spec-draft-n-max ${LLAMA_SPEC_N_MAX:-7} --jinja # see docs/architecture.md#llama-server (flags), docs/network-access.md#backends (no host port) diff --git a/models.yml b/models.yml index ac93d1a..854d781 100644 --- a/models.yml +++ b/models.yml @@ -4,4 +4,4 @@ models: - file: Qwen3.8-27B-UD-Q4_K_XL.gguf url: https://huggingface.co/unsloth/Qwen3.8-27B-GGUF/resolve/main/Qwen3.8-27B-UD-Q4_K_XL.gguf - file: Qwen3.8-27B-DFlash2-Q8_0.gguf - url: https://huggingface.co/z-lab/Qwen3.8-27B-DFlash2-Q8_0.gguf/resolve/main/Qwen3.8-27B-DFlash2-Q8_0.gguf \ No newline at end of file + url: https://huggingface.co/z-lab/Qwen3.8-27B-DFlash2-GGUF/resolve/main/Qwen3.8-27B-DFlash2-Q8_0.gguf