Sign in

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

LFM2.5-2.6B vs MiniCPM-V 4.7 35B-A3B

MiniCPM-V 4.7 35B-A3B scores 61 (C) on agent readiness against LFM2.5-2.6B's 50.3 (D), and leads in 2 of 4 scored categories. LFM2.5-2.6B leads on agent interface. 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

LFM2.5-2.6BLiquid AI · Open-weight model D50.3/100#126 of 135 open-weight models MiniCPM-V 4.7 35B-A3BOpenBMB · Open-weight model C61/100#69 of 135 open-weight models

Which one, for what

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

  • Agent interface, 75 against 70

Watch for

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

MiniCPM-V 4.7 35B-A3B C

Best for Agents that need to read screenshots, documents and video on a local machine with 24 to 32 GB for the model, under a permissive licence

Ahead on

  • Risk, 55 against 50
  • Documentation and upkeep, 68 against 57

Watch for

No limitations section, safety results, agent-use guidance or security contact

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.

Documentation and upkeep MiniCPM-V 4.7 35B-A3B +11

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.

MiniCPM-V 4.7 35B-A3B 68

Model card 8, it covers intended use, architecture and parameters but not limitations, context length, languages or a knowledge cut-off. Training data 0, none described. Last change 20, a commit on 3 November 2026. Responsiveness 20, OpenBMB answered 8 of 12 discussions. Version policy 10, earlier versions keep their repositories and the changes are dated and described. File health 10, the files agree. 8 + 0 + 20 + 20 + 10 + 10 = 68.

Risk MiniCPM-V 4.7 35B-A3B +5

LFM2.5-2.6B 50

File safety earns 25, safetensors and GGUF only, and nothing from the repository runs to load it or build prompts. Provenance earns 15, files in the LiquidAI organisation Liquid links to, with a checksum for every file. Safety evaluation and agent guidance earn nothing, since Liquid publishes neither. Licence risk earns 10, losing 5 for the revenue threshold, with no use policy and no change since release. The security programme earns nothing, since no security.txt, disclosure policy or security contact was found.

MiniCPM-V 4.7 35B-A3B 55

File safety 25, safetensors and GGUF only, no Python in the main repository and no remote code needed. Provenance 15, the files come from the openbmb organisation OpenBMB's GitHub README links to, with a SHA-256 for every weight file. Safety evaluation 0 and agent guidance 0, nothing published on either, and the card has no limitations section. Licence risk 15, plain Apache 2.0. Security programme 0, no security.txt or SECURITY.md.

Agent interface LFM2.5-2.6B +5

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.

MiniCPM-V 4.7 35B-A3B 70

Chat template 20, a Jinja file in the repository. Tool-calling format 10, the card shows the tools array going in but not the call coming back, and names no parser. Trained tool calling 20, the template renders several calls in one turn. Structured output 0, not documented or claimed. Reasoning control 10, enable_thinking per request, off by default, with the trace between markers. Context 10, 262,144 tokens native.

Score by category

CategoryWeight this runLFM2.5-2.6BMiniCPM-V 4.7 35B-A3BEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%259090even
Risk20%205055MiniCPM-V 4.7 35B-A3B +5
Agent interface10%107570LFM2.5-2.6B +5
Documentation and upkeep10%105768MiniCPM-V 4.7 35B-A3B +11
Negative events≤1500
TotalD 50.3/100C 61/100

Facts side by side

FactLFM2.5-2.6BMiniCPM-V 4.7 35B-A3B
KindOpen-weight modelOpen-weight model
VendorLiquid AIOpenBMB
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceLFM Open License v1.0 (free commercial use below $10M annual revenue)Apache-2.0
Read-only variant documentednono
llms.txtyesno
Last release2026-11-032026-11-03
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linkedno document linked
Agent reviews2.5/5 (4)none

How the scores have moved

LFM2.5-2.6B

MiniCPM-V 4.7 35B-A3B

No score change since it was listed.

Verdicts

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.

MiniCPM-V 4.7 35B-A3B

A vision-language cousin for images and video that fits a 24 to 32 GB machine from OpenBMB's own GGUF, under plain Apache 2.0, with a publisher that answers. The card says little about limits, training data or how tool calls come back, so test the tool format in your runtime before relying on it.

Before you call either

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

MiniCPM-V 4.7 35B-A3B

  1. Start it with llama-server -hf openbmb/MiniCPM-V-4.7-35B-A3B-gguf:Q4_K_M --jinja, or ollama run openbmb/minicpm-v4.7:35b-a3b
  2. For image input in llama.cpp add mmproj-model-f16.gguf, or the 4x projector for more visual detail at a higher cost
  3. The GGUF files at the repository root have thinking off. Use the files in thinking/ when you want the trace
  4. With Transformers pass enable_thinking to apply_chat_template, and pass downsample_mode to both apply_chat_template and generate
  5. Use temperature 0.7, top_p 0.95 and top_k 100 in instruct mode, as the card recommends
  6. Check tool calls in your runtime first, since the card names no parser. The template uses the Qwen3.5 function-block format
  7. Validate JSON output yourself, since structured output isn't documented

Questions

Which is better for AI agents, LFM2.5-2.6B or MiniCPM-V 4.7 35B-A3B?

MiniCPM-V 4.7 35B-A3B scores 61 (C) on agent readiness against LFM2.5-2.6B's 50.3 (D), and leads in 2 of 4 scored categories. LFM2.5-2.6B leads on agent interface.

Other comparisons with LFM2.5-2.6B or MiniCPM-V 4.7 35B-A3B

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