MiniCPM5-2B vs Qwen3-VL-4B-Instruct

MiniCPM5-2B

A tiny dense cousin for local tool calling and long context, with published training data and an active publisher. OpenBMB's own 4-bit builds need about 2 GB, so it runs on a laptop or phone in vLLM, SGLang, llama.cpp, Ollama or Transformers. The main risks are always-on thinking, no safety results and use conditions beyond Apache 2.0.

Qwen3-VL-4B-Instruct

A small vision-language cousin for reading screenshots, documents, charts and video, running in about 3.5 GB from Alibaba's Q4_K_M GGUF in every major runtime under plain Apache 2.0. It has no thinking mode, and Qwen hasn't answered repository questions or published safety work, so add your own guardrails before letting it drive a GUI.

MiniCPM5-2B

1. Smallest start is ollama run openbmb/minicpm5-2b (1.6 GB, q4_k_m)
2. On vLLM 0.29.0 or later run vllm serve openbmb/MiniCPM5-2B --max-model-len 131072 --enable-auto-tool-choice --tool-call-parser minicpm5, or tool calls come back as XML text
3. On SGLang 0.5.16 or later add --tool-call-parser minicpm5 --reasoning-parser qwen3; SGLang is OpenBMB's recommended backend for tool calls
4. Tool calls are XML, <function name=...><param name=...>, not Hermes JSON
5. Sample with temperature 1.0, top_p 0.95 and min_p 0.0; llama.cpp's default min_p 0.05 can loop, and repetition_penalty 1.05 helps if it does
6. Expect a <think> block before every answer and leave room in max_tokens; enable_thinking false is accepted by the template but OpenBMB doesn't support it for the 2B
7. Validate JSON yourself or use the runtime's guided decoding, since structured output isn't documented
8. Use the main repository's template; the GGUF, MLX and GPTQ copies predate the 29 September fix

Qwen3-VL-4B-Instruct

1. Start it with llama-server -hf Qwen/Qwen3-VL-4B-Instruct-GGUF:Q4_K_M --jinja -c 32768, or ollama run qwen3-vl:4b-instruct
2. In Ollama the plain qwen3-vl:4b tag is the Thinking edition, so name 4b-instruct
3. With the GGUF, load the mmproj vision file too, or images won't be read
4. Parse tool calls as JSON inside <tool_call> tags, or use SGLang's --tool-call-parser qwen
5. Use the card's sampling, temperature=0.7, top_p=0.8, top_k=20, presence_penalty=1.5 for vision and temperature=1.0, top_p=1.0, top_k=40, presence_penalty=2.0 for text
6. Validate JSON output yourself, since structured output isn't documented
7. vLLM needs 0.11.0 or later and Transformers 4.57.0 or later