MiniMax-M2.7 vs Qwen3.5-4B

MiniMax-M2.7

A 230B mixture-of-experts model for coding and agent harnesses, with parallel tool calls, about 200K of context and parsers in vLLM and SGLang. It needs a 4 GPU server for FP8 or about 166 GB for a 4-bit library build, and it always thinks. The main risk is the licence, switched to non-commercial two days after release.

Qwen3.5-4B

A small vision-language cousin for tool calls, light agent steps and image or video reading on almost any machine, with switchable thinking. Ollama's 3.3 GB build or the 9.3 GB BF16 files run in every major runtime under plain Apache 2.0. The main risks are no safety results, no structured-output guarantee and no answers from Alibaba since March.

MiniMax-M2.7

1. Check the use is personal, research or non-profit before starting it; anything commercial needs MiniMax's written authorisation, and commercial users must show Built with MiniMax M2.7
2. Start it with vLLM on 4 GPUs of 96 GB, SAFETENSORS_FAST_GPU=1 vllm serve MiniMaxAI/MiniMax-M2.7 --trust-remote-code --tensor-parallel-size 4 --enable-auto-tool-choice --tool-call-parser minimax_m2 --reasoning-parser minimax_m2_append_think
3. In SGLang use --tool-call-parser minimax-m2 and --reasoning-parser minimax-append-think, with --trust-remote-code
4. MiniMax's guides budget 220 GB for the weights and 240 GB per 1M tokens of KV cache, with 196K the most per sequence
5. On one large-memory machine, LM Studio's catalogue entry minimax/minimax-m2.7 lists a 138 GB Q4_K_M GGUF and states 138 GB minimum memory
6. Sample with temperature 1.0, top_p 0.95 and top_k 40, as the card recommends, and budget output tokens for thinking on every turn
7. Pin Transformers 4.57.1 as MiniMax's guide does; a report that it fails on Transformers v5 has no answer
8. Without the hardware, call it through Novita, Featherless AI or DeepInfra; MiniMax's own API retires M2.7 on 18 November 2026

Qwen3.5-4B

1. Smallest start is ollama run qwen3.5:4b (Q4_K_M, about 4 GB with context)
2. Full precision vllm serve Qwen/Qwen3.5-4B --port 8000 --max-model-len 262144 --reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser qwen3_coder
3. Turn thinking off with "chat_template_kwargs": {"enable_thinking": false} in the request body, since it's on by default and /think and /nothink aren't supported
4. There's no generation_config.json, so pass the card's sampling yourself, for example temperature=0.7, top_p=0.8, top_k=20, presence_penalty=1.5 without thinking
5. Keep the context at 128K or more if you rely on thinking, and turn on YaRN only past 262,144 tokens
6. Validate any JSON it returns, since structured output isn't documented