From 879c35229909219c6867f71cf5d7d4ee8f243524 Mon Sep 17 00:00:00 2001 From: Tai An Date: Mon, 27 Apr 2026 00:22:33 -0700 Subject: [PATCH] fix(gallery): correct Qwen3.5 typo in qwen3.5-27b-claude-4.6 model override (closes #9362) The overrides.parameters.model field referenced 'Qwen3.-27B-Claude-...' (missing the '5'), so model loads failed because the configured filename did not match the file actually downloaded by the entry's files: list ('Qwen3.5-27B-Claude-...'). Aligns the override filename with the files: entries and with the upstream HF repo (mradermacher/Qwen3.5-27B-...). --- gallery/index.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/gallery/index.yaml b/gallery/index.yaml index ac5b3db6ffee..d5657cb54895 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -745,7 +745,7 @@ - default overrides: parameters: - model: llama-cpp/models/Qwen3.-27B-Claude-4.6-Opus-Reasoning-Distilled-heretic.i1-Q4_K_M.gguf + model: llama-cpp/models/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-heretic.i1-Q4_K_M.gguf backend: llama-cpp template: use_tokenizer_template: true