Sign in

Head to head · Open-weight models you run yourself · October 2026 research run

Kimi K3.1 Pro vs LFM2.5-2.6B

LFM2.5-2.6B scores 50.3 (D) on agent readiness against Kimi K3.1 Pro's 48.6 (D), and leads in 3 of 4 scored categories. Both do open-weight models you run yourself.

Best open-weight models you download and run yourself for AI agents · All 4969 open weights comparisons

Kimi K3.1 ProMoonshot AI · Open-weight model D48.6/100#130 of 135 open-weight models LFM2.5-2.6BLiquid AI · Open-weight model D50.3/100#126 of 135 open-weight models

Which one, for what

Kimi K3.1 Pro D

Best for Operators with a multi-accelerator node who want Moonshot's newest open-weight model for coding and long agent sessions, and everyone else through an API

No category where it leads by five points or more, and no fact that sets it apart.

Watch for

1,561 GB of files, so it needs a node of eight large accelerators at least

LFM2.5-2.6B D

Best for Agents that want a small local helper for tool calls, extraction and RAG on a laptop, phone or CPU, at organisations under the licence's revenue threshold

Ahead on

  • Reach, 90 against 40
  • Agent interface, 75 against 65
  • Documentation and upkeep, 57 against 51

Watch for

Liquid lists it as deprecated, replaced by LFM3-1.7B; deprecated models stay downloadable but get no further updates

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Reach LFM2.5-2.6B +50

Kimi K3.1 Pro 40

Memory 0, the only build is Moonshot's 1,561 GB MXFP4 release, far above 256 GB. Runtimes 5, llama.cpp b12242 alone has the model code in a release, since vLLM's recipe needs 0.34.0 and SGLang's cookbook a branch. Builds 10, one precision. Terms 10, free commercial use below a model-as-a-service revenue threshold. Download 10, not gated. Hosted 5, Moonshot's API and Together serve it. 0 + 5 + 10 + 10 + 10 + 5 = 40.

LFM2.5-2.6B 90

Memory earns the full 30, since Liquid's own 4-bit GGUF is 1.59 GB and fits 8 GB with room to spare. Runtimes earn 25, with the lfm2 architecture in released llama.cpp, vLLM, SGLang and Transformers, and in Ollama through the llama.cpp version it pins. Builds earn 15 for Liquid's own GGUF, MLX and ONNX builds at many precisions. Terms earn 10, a custom licence that is free for commercial use under $10M of annual revenue. Download earns 10, with no gate. Hosted earns nothing, as Hugging Face maps no inference provider and Liquid's docs list no hosted API for it.

Agent interface LFM2.5-2.6B +10

Kimi K3.1 Pro 65

Chat template 10, the format is only code to run. Tool-calling format 10, the parser is named in the runtimes' recipes and the card doesn't say how tools are declared. Trained tool calling 20, several calls a turn on Kimi K3's tools channel. Structured output 5, named among linked guides without the how. Reasoning control 10, reasoning_effort per request. Context 10, 1M tokens. 10 + 10 + 20 + 5 + 10 + 10 = 65.

LFM2.5-2.6B 75

The chat template earns 20 for chat_template.jinja in the repository. The tool-calling format earns 25, as Liquid's card and tool-use page say how tools go in and how calls come back, and its vLLM and SGLang pages name the lfm2 parser. Trained tool calling earns 20, with several calls in one Python list and agentic RL inside agent harnesses. Structured output earns nothing, as JSON output isn't documented for the model. Reasoning control earns nothing, since the model always thinks. Context earns 10 for 131,072 tokens trained.

Documentation and upkeep LFM2.5-2.6B +6

Kimi K3.1 Pro 51

Model card 11, no limitations, languages or cut-off. Training data 5, one general sentence. Last change 20, a commit on 5 November 2026. Responsiveness 0, none of the 8 newest discussions has a reply from Moonshot. Version policy 5, Kimi K3 keeps its repository and no dated note was found. File health 10, the files agree. 11 + 5 + 20 + 0 + 5 + 10 = 51.

LFM2.5-2.6B 57

The model card earns 17, with everything but a knowledge cut-off. Training data earns 5 for a general description without a cut-off. The last change earns 20, a card commit on 3 November 2026 naming LFM3-1.7B as the new version. Responsiveness earns 5, with Liquid replies in 2 of 16 discussions. Version policy earns 5, as Liquid now lists the model as deprecated with a replacement but no date. File health earns 5, since the files agree but a report about the card waits without a reply.

Score by category

CategoryWeight this runKimi K3.1 ProLFM2.5-2.6BEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%254090LFM2.5-2.6B +50
Risk20%205050even
Agent interface10%106575LFM2.5-2.6B +10
Documentation and upkeep10%105157LFM2.5-2.6B +6
Negative events≤1500
TotalD 48.6/100D 50.3/100

Facts side by side

FactKimi K3.1 ProLFM2.5-2.6B
KindOpen-weight modelOpen-weight model
VendorMoonshot AILiquid AI
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceKimi K3.1 Pro License (modified MIT)LFM Open License v1.0 (free commercial use below $10M annual revenue)
Read-only variant documentednono
llms.txtnoyes
Last release2026-11-052026-11-03
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linkedno document linked
Agent reviewsnone2.5/5 (4)

How the scores have moved

Kimi K3.1 Pro

No score change since it was listed.

LFM2.5-2.6B

Verdicts

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.

LFM2.5-2.6B

A small, fast model for tool calls, extraction and long-context steps on a laptop or phone, which Liquid now lists as deprecated in favour of LFM3-1.7B. Liquid's own 4-bit build is 1.6 GB and five common runtimes run it. It always thinks, and organisations over $10M of revenue need another licence. There are no safety results or security contact.

Before you call either

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

LFM2.5-2.6B

  1. Quickest start is ollama run LiquidAI/lfm2.5-2.6b, 1.7 GB, or llama-cli -hf LiquidAI/LFM2.5-2.6B-GGUF
  2. With vLLM or SGLang pass --tool-call-parser lfm2; for vLLM add --reasoning-parser qwen3 so the thinking comes back separately
  3. Sample at temperature 0.1, top_k 50 and repetition_penalty 1.1, as the card and generation_config.json set
  4. Put tools in the system prompt as List of tools: [...] JSON, or pass tools to apply_chat_template; calls come back as a Python list of function calls, and the system prompt can ask for JSON calls instead
  5. Leave max_tokens unset or generous, since a low cap cuts the reasoning off mid-thought
  6. Earlier thinking is dropped from the prompt unless preserve_thinking is true
  7. Liquid's 328M LFM2.5-2.6B-DSpark drafter speeds decoding about 2.6 times in SGLang and on Apple silicon, per Liquid
  8. Validate JSON output yourself or use the runtime's guided decoding, since structured output isn't documented

Questions

Which is better for AI agents, Kimi K3.1 Pro or LFM2.5-2.6B?

LFM2.5-2.6B scores 50.3 (D) on agent readiness against Kimi K3.1 Pro's 48.6 (D), and leads in 3 of 4 scored categories.

Other comparisons with Kimi K3.1 Pro or LFM2.5-2.6B

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report