Kimi K3.1 Pro vs Qwopus3.8-27B-Flash-V2

Kimi K3.1 Pro

No score change since it was listed.

Qwopus3.8-27B-Flash-V2

• no change on 3 November 2026: time

Kimi K3.1 Pro

Moonshot's newest flagship, eight days old when read, for operators with a rack. Only llama.cpp has its model code in a release, with vLLM and SGLang support still on a release candidate and a branch. The licence is permissive below a revenue threshold, and Moonshot hasn't answered a discussion on the repository yet.

Qwopus3.8-27B-Flash-V2

A Qwen3.8-27B cousin tuned to think less per turn in long agent loops, with an MTP head for speculative decoding in llama.cpp. It fits 24 GB with Jackrong's 4-bit GGUF. The risks are one person's experimental release with no safety work, training traces taken from Claude and GPT, and a tool format that differs from Qwen's.

Kimi K3.1 Pro

1. Use Moonshot's API or Together unless you have a node of eight B300-class accelerators
2. With vLLM use 0.34.0 or later and the recipe's flags, --tool-call-parser kimi_k3 --reasoning-parser kimi_k3
3. Pass the whole assistant message back in later turns, reasoning_content and tool_calls included, as the card requires
4. Set reasoning_effort to low, high or max per request. Max is the default and thinking can't be turned off
5. Kimi K3's model code doesn't load it, because the attention layers changed
6. Validate JSON output yourself, since the card doesn't document structured output for the weights

Qwopus3.8-27B-Flash-V2

1. Quickest start is llama-server -hf Jackrong/Qwopus3.8-27B-Flash-V2-GGUF:Q4_K_M --jinja, about 17 GB, and add mmproj-F32.gguf for images
2. The card's tests used Q5_K_M with the bundled MTP head and --spec-type draft-mtp in llama.cpp
3. The template asks for tool calls as JSON inside tool_call tags, so use a Hermes-style parser (vLLM's hermes), not Qwen3.8's qwen3_coder
4. For coding the card recommends enable_thinking true, reasoning_effort xhigh and temperature 0.3, which you must pass yourself, since generation_config.json says 1.0
5. reasoning_effort takes xhigh (default), medium or low, and any other value makes the template raise an error
6. Earlier reasoning stays in the context unless preserve_thinking is false
7. Cap max_tokens, since a report says it loops more than V1