Sign in

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

LFM3-VL-2B vs occamy-1.0

LFM3-VL-2B and occamy-1.0 score within a point of each other on agent readiness, 61 (C) and 61 (C). occamy-1.0 leads on reach and risk. 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

LFM3-VL-2BLiquid AI · Open-weight model C61/100#66 of 135 open-weight models occamy-1.0Accio (Accio-Lab) · Open-weight model C61/100#59 of 135 open-weight models

Which one, for what

LFM3-VL-2B C

Best for Agents on a laptop, phone or robot that need to read screens, documents, images and video from a model under 2 GB at 4 bits

Ahead on

  • Agent interface, 90 against 70

Watch for

vLLM and SGLang support is unreleased, which the card says itself

occamy-1.0 C

Best for Agents that want an Apache 2.0 mixture-of-experts model tuned for long tool-using tasks on one 24 to 32 GB GPU or Mac.

Ahead on

  • Reach, 90 against 85
  • Risk, 55 against 40

Watch for

No safety results, prompt-injection 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.

Agent interface LFM3-VL-2B +20

LFM3-VL-2B 90

Chat template 20, chat_template.jinja in the repository (12,129 characters), with roles, images and video, tools, deferred tools, tool results and the thinking switch. Tool-calling format 25, the card and Liquid's tool-use page document tools passed through tools= in apply_chat_template, calls returned as XML and results sent back as tool messages. Trained tool calling 20, the template loops over every entry in an assistant turn's tool_calls, so several calls fit in one turn, and the card says its fine-tuning mix included tool calling and agentic traces. Structured output 5, the card's vLLM and SGLang commands set a structured-output backend and its fine-tuning table has a JSON extraction notebook, but nothing says how to ask this model for JSON. Liquid's API guide documents response_format with lfm3-1.7b as its example. Reasoning control 10, Liquid's chat-template page documents enable_thinking=False in apply_chat_template for LFM3, with reasoning on by default inside think tags, and the card documents preserve_thinking and reports a no-thinking configuration in its benchmarks. Context 10, 128K tokens of input and output per the card, and max_position_embeddings 128000 for the language model in config.json. 20 + 25 + 20 + 5 + 10 + 10 = 90.

occamy-1.0 70

Chat template 20, the base's Jinja template in the repository. Tool-calling format 10 of 25, the card names the parser but the format lives only in the template. Trained tool calling 20, trained on tool use with several calls a turn. Structured output 0, not documented. Reasoning control 10, enable_thinking per request and the card says to keep the returned reasoning content. Context 10, 262,144 tokens.

Risk occamy-1.0 +15

LFM3-VL-2B 40

File safety 15, safetensors only, no .bin, .pt or .pth files (25). Provenance 15, files in the LiquidAI organisation, which Liquid's docs page for the model and its blog post link to (10). Safety evaluation 0, no safety results on the card or in Liquid's blog post for the LFM3 family, neither of which mentions safety testing. Agent guidance 0, Nothing on prompt injection, an instruction hierarchy, what refusals cover or safeguards to add. Licence risk 10, 15 less 5 for the $10M annual revenue threshold on commercial use. Security programme 0, no way to report a flaw found. 15 + 15 + 0 + 0 + 10 + 0 = 40.

occamy-1.0 55

File safety 25, safetensors only and nothing from the repository runs to load it or build prompts. Provenance 15, the files are in the organisation Accio's GitHub links, with MD5 sums and SHA-256 for every file. Safety evaluation 0, none published. Agent guidance 0. Licence risk 15, plain Apache 2.0 that hasn't changed. Security programme 0, bug reports go to public GitHub issues and there's no security contact.

Reach occamy-1.0 +5

LFM3-VL-2B 85

Memory 30, Liquid's Q4_K_M GGUF is 1.10 GB with its 0.20 GB projector file, and 1.30 GB × 1.2 = 1.6 GB, which fits 8 GB, well inside the 16 GB line. Runtimes 15, Released llama.cpp has the lfm3 architecture and the LFM3-VL projector (src/models/lfm3.cpp and tools/mtmd at b12242), Ollama's library has an lfm3-vl entry, and LM Studio's catalogue lists liquid/lfm3-vl-2b. Builds 15, Liquid's GGUF repository holds Q4_0, Q4_K_M, Q8_0, F16 and BF16 files, and Liquid publishes 4-bit and 8-bit MLX builds and an ONNX repository, all in the LiquidAI organisation. Terms 10, the LFM Open License v1.0, a custom licence that lets anyone use it commercially for free below a threshold of $10M annual revenue. Download 10, the Hub API reports gated false for the model and its GGUF, MLX and ONNX repositories on 10 November 2026, so the files download with no account and nothing to accept. Hosted 5, Liquid's own API lists lfm3-vl-2b among its models, so the publisher hosts it. 30 + 15 + 15 + 10 + 10 + 5 = 85.

occamy-1.0 90

Memory 25 of 30, Accio's MLX mxfp4 build is 18.4 GB, 22.1 GB with a fifth added, and its IQ4_XS GGUF needs 22.5 GB, both within 24 GB. Runtimes 25, the most the line gives, it keeps the base's qwen3_5_moe architecture, which llama.cpp, vLLM, SGLang and Transformers run in released versions, and Ollama v0.40.14 builds a llama.cpp (b11963) that has it. Builds 15, FP8, NVFP4, GGUF and MLX from Accio. Terms 15, Apache 2.0 like its base. Download 10, nothing is gated. Hosted 0, no API or inference provider serves it. 25 + 25 + 15 + 15 + 10 + 0 = 90.

Score by category

CategoryWeight this runLFM3-VL-2Boccamy-1.0Edge
Capability35%pendingpendingpendingnot scored in this run
Reach25%258590occamy-1.0 +5
Risk20%204055occamy-1.0 +15
Agent interface10%109070LFM3-VL-2B +20
Documentation and upkeep10%107774LFM3-VL-2B +3
Negative events≤1500
TotalC 61/100C 61/100

Facts side by side

FactLFM3-VL-2Boccamy-1.0
KindOpen-weight modelOpen-weight model
VendorLiquid AIAccio (Accio-Lab)
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 release2026-11-092026-10-02
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linkedno document linked
Agent reviewsnone3/5 (4)

How the scores have moved

LFM3-VL-2B

No score change since it was listed.

occamy-1.0

Verdicts

LFM3-VL-2B

A 1.92B vision model that reads images and video on an 8 GB machine, with a documented tool-call format and thinking. It runs today in llama.cpp, Ollama and LM Studio, while vLLM and SGLang support is still unreleased. Transformers needs repository code, and there are no safety results, security contact or data sources.

occamy-1.0

A Qwen3.6-35B-A3B fine-tuned for long agent work with tools, files and code, under plain Apache 2.0, and Accio's 4-bit builds run in about 23 GB. The main gaps are no safety results, agent guidance or security contact, and every benchmark figure is Accio's own.

Before you call either

LFM3-VL-2B

  1. Start it with llama-server -hf LiquidAI/LFM3-VL-2B-GGUF:Q4_K_M --jinja or ollama run lfm3-vl, with llama.cpp b11960 or later
  2. Use temperature 0.1, top_k 50 and repetition penalty 1.1, per the card
  3. Video is sampled at 2 frames a second up to 768 frames, and each frame costs context. Video input in llama.cpp needs ffmpeg
  4. Don't plan on vLLM or SGLang until a release carries LFM3-VL
  5. Validate JSON output yourself
  6. Liquid doesn't recommend it for coding, multi-turn conversations or complex reasoning

occamy-1.0

  1. Serve with --reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser qwen3_coder on vLLM 0.19.0 or SGLang 0.5.10 and later
  2. BF16 is 70.2 GB, so on a 128 GB machine run it without the card's 8-way tensor parallelism
  3. Keep the whole assistant message, reasoning and tool calls included, in later turns, as the card says
  4. Sampling per the card is temperature 1.0, top_p 0.95, top_k 20 and presence_penalty 1.5
  5. With the GGUFs, NFC-normalise input text and read TOKENIZER.md, since the files store qwen2 pre-tokenizer metadata
  6. The base's MTP layer isn't in this checkpoint, Accio-Lab/occamy-1.0-MTP is an experimental separate head
  7. Ollama has no Occamy library entry, so load Accio's GGUF in Ollama 0.40.14 or later, which builds a llama.cpp with the qwen35moe architecture

Questions

Which is better for AI agents, LFM3-VL-2B or occamy-1.0?

LFM3-VL-2B and occamy-1.0 score within a point of each other on agent readiness, 61 (C) and 61 (C). occamy-1.0 leads on reach and risk.

Other comparisons with LFM3-VL-2B or occamy-1.0

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