{"slug": "qwen-3-5-0-8b", "title": "Qwen 3.5 0.8B", "summary": "A user tested Qwen 3.5 0.8B (Qwen3.5-0.8B-Q4_K_M.gguf) locally and found it works on their MCP server, with a temperature of 0 giving the most consistent results for agentic function calling despite documentation recommending 0.7 or 1.0. The 752M-parameter, 532 MB model thinks by default and appears more capable than the LFM 2.5 models the user usually runs, though it is bigger and slower; MTP offered no noticeable speedup.", "body_md": "Today I **downloaded** and used **Qwen 3.5 0.8B** (`Qwen3.5-0.8B-Q4_K_M.gguf`) on my local system. I wanted to see if it would work on my MCP server, which I had designed for small models (it did). I will add it to my collection of useful models.\n\nIn using it as an agentic function-calling model, I found that a **temperature of 0** is helpful. The documentation suggests higher temperatures like 0.7 or 1.0, but 0 seems to be most consistent and reliable. So if you try out 0.8B, make sure to lower the temperature before deleting it.\n\n• It thinks by default, which is interesting for a 752M parameter model.\n\n• Using MTP on Qwen 0.8B seems to be either slower or not noticeably faster—probably no point in trying to speed up a 532 MB model.\n\n• It is bigger and slower than the LFM 2.5 models I usually run, but it seems like it may be more capable (this makes sense, as it has three times more parameters).\n\n• It is nice to have another model that can handle my workload; Qwen 3.5 0.8B is a valued addition to my model collection.", "url": "https://wpnews.pro/news/qwen-3-5-0-8b", "canonical_source": "https://www.dotnetperls.com/2026_9_14_qwen-35-08b", "published_at": "2026-09-14 07:00:00+00:00", "updated_at": "2026-09-14 15:15:26.888869+00:00", "lang": "en", "topics": ["ai-products", "ai-tools", "large-language-models", "ai-agents"], "entities": ["Qwen 3.5 0.8B", "Qwen3.5-0.8B-Q4_K_M.gguf", "MCP", "LFM 2.5"], "alternates": {"html": "https://wpnews.pro/news/qwen-3-5-0-8b", "markdown": "https://wpnews.pro/news/qwen-3-5-0-8b.md", "text": "https://wpnews.pro/news/qwen-3-5-0-8b.txt", "jsonld": "https://wpnews.pro/news/qwen-3-5-0-8b.jsonld"}}