MiniMax-M2.7 vs Qwen3.5-122B-A10B

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.

Qwen3.5-122B-A10B

A strong mid-size cousin for coding, agent steps and reading images or video, with thinking you can switch off per request. Alibaba's 4-bit build needs about 95 GB, which fits one 128 GB unified-memory machine, and several providers host it. The main risk is silence, with no safety results, agent guidance or answers from Alibaba.

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

Qwen3.5-122B-A10B

1. Quickest start on a 128 GB machine is ollama run qwen3.5:122b (Q4_K_M, 81 GB of files, about 97 GB with context)
2. Alibaba's 4-bit build serves with vllm serve Qwen/Qwen3.5-122B-A10B-GPTQ-Int4 --max-model-len 262144 --reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser qwen3_coder --quantization moe_wna16, though that kernel isn't documented for AMD gfx1151
3. Use the qwen3_coder tool parser and the qwen3 reasoning parser, as the card's commands do
4. 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
5. Sampling per the card is temperature 0.6, top_p 0.95 and top_k 20 when thinking, and temperature 0.7, top_p 0.8, top_k 20 and presence_penalty 1.5 without
6. Keep the context at 128K or more if you rely on thinking, and turn on YaRN only past 262,144 tokens
7. Add --language-model-only in vLLM to skip the vision encoder and free memory for the KV cache when you only need text
8. Validate any JSON it returns, since structured output isn't documented