From 25ecb9f0158c2d27788f385b4d06fc12dbfd8d0b Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Tue, 30 Jun 2026 17:46:20 +0000 Subject: [PATCH] fix(gallery): use Q8_0 for lfm2.5-8b-a1b to fix poor tool-call quality The Q4_K_M quant degraded tool-call reliability for LFM2.5-8B-A1B. Switch the gallery entry to the Q8_0 GGUF (sha256 verified via HF x-linked-etag) while keeping the native jinja tool-parsing config. Signed-off-by: Ettore Di Giacinto Assisted-by: Claude:claude-opus-4-8 [Claude Code] --- gallery/index.yaml | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/gallery/index.yaml b/gallery/index.yaml index ac825cdae..78aac2996 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -1716,7 +1716,7 @@ - use_jinja:true parameters: min_p: 0.15 - model: llama-cpp/models/LFM2.5-8B-A1B-GGUF/LFM2.5-8B-A1B-Q4_K_M.gguf + model: llama-cpp/models/LFM2.5-8B-A1B-GGUF/LFM2.5-8B-A1B-Q8_0.gguf repeat_penalty: 1.05 temperature: 0.1 top_k: 50 @@ -1724,9 +1724,9 @@ template: use_tokenizer_template: true files: - - filename: llama-cpp/models/LFM2.5-8B-A1B-GGUF/LFM2.5-8B-A1B-Q4_K_M.gguf - uri: https://huggingface.co/LiquidAI/LFM2.5-8B-A1B-GGUF/resolve/main/LFM2.5-8B-A1B-Q4_K_M.gguf - sha256: 4923ec14f06b968b74d663e5949867d2d9c3bf13a20b8be1a9f9af39989b2bb0 + - filename: llama-cpp/models/LFM2.5-8B-A1B-GGUF/LFM2.5-8B-A1B-Q8_0.gguf + uri: https://huggingface.co/LiquidAI/LFM2.5-8B-A1B-GGUF/resolve/main/LFM2.5-8B-A1B-Q8_0.gguf + sha256: 33ab3b8ce6a964fb8ebac89360c9b3cf72c4fa418d5e4c0a94d46883124d5c02 - name: "qwopus3.5-9b-coder-mtp" url: "github:mudler/LocalAI/gallery/virtual.yaml@master" urls: