jody/yacy_search_server
1
0 Fork 0
mirror of https://github.com/yacy/yacy_search_server.git synced 2026-10-25 05:54:15 +00:00
Code Issues Packages Projects Releases Wiki Activity

added qwen3.8:27b to recommended model list

Browse Source
This commit is contained in:
Michael Peter Christen committed 2026-08-14 20:52:39 +02:00
1 parent 9aa6b93c72
commit eff8d81c4e
1 file changed
+1 -1
Download Patch File Download Diff File Expand all files Collapse all files
htroot/LLMSelection_p.html
+1 -1
View File
@@ -106,7 +106,7 @@
["ministral-3:14b-instruct-2512-q4_K_M", " 8.55", "10GB", "European model, strong multilangual, has vision, is agentic", "mistral.ai", "apache-2.0"],
["hf.co/mradermacher/Ling-mini-2.0-GGUF:Q4_K_M", "20.00", "10GB", "very fast 16B MoE model with 1.4B activated parameters per expert", "InclusionAI", "mit"],
["olmo-3.1:32b-instruct-q4_K_M", "10.25", "19GB", "open and accessible training data, open-source training code", "allenai.org", "apache-2.0"],
["qwen3.6:27b-mtp-q4_K_M", "49.22", "17GB", "Exceptional good 27B model with vision, ranking above GPT-4-turbo, GPT-4.1-nano, GPT-o1, GPT-4o-mini", "Alibaba", "apache-2.0"],
["qwen3.8:27b-mtp-q4_K_M", "57.42", "17GB", "Exceptional good 27B model with vision, ranking above GPT-4-turbo, GPT-4.1-nano, GPT-o1, GPT-4o-mini", "Alibaba", "apache-2.0"],
["muse-glimmer:30b-q4_K_M-dflash", "55.55", "21GB", "Agent-first model from Meta, tuned for tool use, long tasks, and failure recovery", "Meta", "apache-2.0"],
["qwen3.6:35b-a3b-mtp-q4_K_M", "45.91", "22GB", "Almost as good as the 27B model, but much faster", "Alibaba", "apache-2.0"]
];