DeepSeek-V3.2 vs MiMo-V2.6 Distill Qwen 9B

DeepSeek-V3.2

DeepSeek-V3.2 is an MIT-licensed reasoning model trained for parallel tool calls, with thinking chosen per request, for long agent work. It needs about 690 GB of FP8 files, eight 80 GB GPUs in vLLM's recipe and prompts built from DeepSeek's Python. The main risk is neglect, with no file changes since December 2025 and no safety evaluation.

MiMo-V2.6 Distill Qwen 9B

A 9B cousin tuned on MiMo-V2.6's agent work for coding, terminal tasks and visual coding, released as a base for RL research. It needs about 23 GB in BF16, since Xiaomi ships no smaller build. The main risks are no safety results while a seventh of its tuning is offensive security, and nobody at Xiaomi answering reports.

DeepSeek-V3.2

1. Start it with vLLM's recipe, vllm serve deepseek-ai/DeepSeek-V3.2 --tensor-parallel-size 8 --tokenizer-mode deepseek_v32 --enable-auto-tool-choice --tool-call-parser deepseek_v32 --reasoning-parser deepseek_v3
2. It doesn't fit the 107.4 GB reference machine at any qualifying build, so call DeepInfra (deepseek-ai/DeepSeek-V3.2) or SambaNova (DeepSeek-V3.2) instead
3. Outside vLLM, build prompts with encoding/encoding_dsv32.py and wrap parse_message_from_completion_text in error handling, since DeepSeek says it handles well-formed output only
4. Pick thinking or chat with thinking_mode, and read the reasoning from reasoning_content
5. Send developer messages only for search-agent prompts, the only use DeepSeek gives that role
6. Use temperature 1.0 and top_p 0.95 and keep prompts within 128K tokens

MiMo-V2.6 Distill Qwen 9B

1. Serve it as the card does, sglang serve --model-path XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B --reasoning-parser mimo, and add --tool-call-parser mimo for parsed tool calls
2. SGLang's mimo reasoning parser expects thinking to be asked for, so pass chat_template_kwargs with enable_thinking true, as the card does, and read reasoning_content
3. Calls come back as function and parameter blocks inside tool_call, the same shape vLLM's and SGLang's qwen3_coder parsers read
4. The generation config samples at temperature 0.6, top_k 20 and top_p 0.95
5. Images and video go in through Qwen3.5's processor; the template's audio tokens have no audio encoder behind them
6. The MTP head isn't in the files, so skip MTP speculative decoding even though config.json lists a layer
7. It's an SFT checkpoint meant for further RL, and discussions report runaway generation on llama.cpp, so cap max_tokens