Sign in

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

Laguna XS 2.1 vs WeVisOne-VL-4B

Laguna XS 2.1 and WeVisOne-VL-4B score within a point of each other on agent readiness, 61 (C) and 61 (C). Both do open-weight models you run yourself.

Best open-weight models you download and run yourself for AI agents · All 6359 open weights comparisons

Laguna XS 2.1Poolside · Open-weight model C61/100#46 of 160 open-weight models WeVisOne-VL-4BTencent (WeChat Vision) · Open-weight model C61/100#84 of 160 open-weight models

Which one, for what

Laguna XS 2.1 C

Best for Agents that want a fast local coding model on a 32 GB GPU or Mac, with tool calling and a permissive licence.

Ahead on

  • Reach, 80 against 70
  • Agent interface, 85 against 70

Watch for

No reply from Poolside to any discussion, including reports about the tokenizer and remote code

WeVisOne-VL-4B C

Best for Agents that need to locate, count or cut out objects in images on a small GPU, under a permissive licence

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

Watch for

The pixel decoder ships as a pickle file

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 Laguna XS 2.1 +15

Laguna XS 2.1 85

Chat template 20, a Jinja file in the repository. Tool-calling format 25, the card shows how tools go in and calls come back and names the poolside_v1 parser for three runtimes. Trained tool calling 20, the template renders several calls a turn. Structured output 0, not documented. Reasoning control 10, enable_thinking per request with the reasoning in reasoning_content. Context 10, 128K trained per Poolside's report, with 262,144 reached by YaRN.

WeVisOne-VL-4B 70

Chat template 20, chat_template.jinja in the repository (5,292 characters), Qwen3-VL's template. Tool-calling format 25, Read for a perception model as what it takes and returns. Trained tool calling 10, Read for a perception model as the inputs it was trained to use. Structured output 15, Read for a perception model as typed outputs. Reasoning control 0, the card says it writes structured output directly with no chain-of-thought reasoning. Context 0, Tencent states no context length for it. 20 + 25 + 10 + 15 + 0 + 0 = 70.

Reach Laguna XS 2.1 +10

Laguna XS 2.1 80

Memory 20 of 30, the smallest 4-bit build with an exact size is Poolside's Q4_K_M GGUF at 20.27 GB, the same file as Ollama's default, which needs 32 GB with a fifth added. Runtimes 25, released llama.cpp, Ollama, vLLM, SGLang and Transformers all run the laguna architecture. Builds 15, Poolside publishes FP8, INT4, NVFP4, MLX and GGUF builds. Terms 10, OpenMDW-1.1 is permissive but not OSI-approved. Download 10, nothing is gated. Hosted 0, Poolside's OpenRouter endpoints expired on 31 October 2026 and no other host was found.

WeVisOne-VL-4B 70

Memory 30, the only build from Tencent is the BF16 safetensors file with its decoder, 9.7 GB, and 9.7 GB × 1.2 = 11.6 GB, within 16 GB. No runtime library has a build. Runtimes 15, the architecture is Qwen3VLForConditionalGeneration, which vLLM 0.33.0, SGLang 0.5.23 and Transformers 5.22.2 run from the safetensors file, three at 5 each. Builds 0, Tencent publishes the BF16 weights only. Terms 15, Apache 2.0 in the card's metadata with the LICENSE file in the repository, and nothing added. Download 10, the Hub API reports gated false on 10 November 2026, so the files download with no account and nothing to accept. Hosted 0, Hugging Face maps no inference provider to it. 30 + 15 + 0 + 15 + 10 + 0 = 70.

Score by category

CategoryWeight this runLaguna XS 2.1WeVisOne-VL-4BEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%258070Laguna XS 2.1 +10
Risk20%205555even
Agent interface10%108570Laguna XS 2.1 +15
Documentation and upkeep10%104648WeVisOne-VL-4B +2
Negative events≤1500
TotalC 61/100C 61/100

Facts side by side

FactLaguna XS 2.1WeVisOne-VL-4B
KindOpen-weight modelOpen-weight model
VendorPoolsideTencent (WeChat Vision)
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceOpenMDW-1.1Apache-2.0
Read-only variant documentednono
llms.txtnono
Last release2026-08-192026-10-27
Terms last updated2026-07-21not read yet
Privacy policy last updated2026-07-21no document linked
Customer content may train modelsyes, with an opt-outnot read yet
Terms restrict automated accessnot found in the textnot read yet
Terms restrict benchmarkingnot found in the textnot read yet
Terms or service can change without noticeyesnot read yet
Arbitration or class-action waiveryesnot read yet
Agent reviews2.8/5 (4)none

How the scores have moved

Laguna XS 2.1

WeVisOne-VL-4B

No score change since it was listed.

Verdicts

Laguna XS 2.1

A small coding and agent cousin with 3B active parameters, so it's quick on modest hardware. Poolside's 4-bit GGUF, also Ollama's default, needs about 24 GB, and every major runtime runs it. The main risks are that nobody at Poolside answers its discussions, there are no safety results, and the SGLang route runs repository code.

WeVisOne-VL-4B

A small Apache 2.0 perception model that finds, counts, reads and cuts out what you name in an image, and says None when it isn't there. Boxes and points run in vLLM, SGLang or Transformers. Masks and mattes need Tencent's package and a pickle file. Two weeks old, with no questions answered yet and no safety results.

Before you call either

Laguna XS 2.1

  1. Quickest start is ollama run laguna-xs-2.1, 20 GB of files, the same Q4_K_M as Poolside's GGUF
  2. On our reference machine use llama-server -hf poolside/Laguna-XS-2.1-GGUF:Q4_K_M --jinja -c 131072, from a llama.cpp release with the laguna architecture (b11772 has it), or BF16 with vLLM (66.9 GB)
  3. With vLLM use --tool-call-parser poolside_v1 --reasoning-parser poolside_v1 --enable-auto-tool-choice, on a build with vllm-project/vllm#47311, or --tool-call-parser glm47 on older builds
  4. Thinking is off in the template unless you pass enable_thinking true or start the server with --default-chat-template-kwargs '{"enable_thinking": true}', which Poolside recommends for agentic coding
  5. Pass earlier reasoning back as reasoning_content in the history, since the card says reasoning may stop in later steps if it's dropped
  6. Sampling per the card is temperature 1.0 and top_k 20
  7. The card warns that Ollama on Apple Silicon may return empty output until llama.cpp#25389 ships
  8. Validate JSON output yourself or use the runtime's guided decoding, since structured output isn't documented

WeVisOne-VL-4B

  1. Use Tencent's package: WeVisOneVL("tencent/WeVisOne-VL-4B", backend="vllm") then model.predict(image, task=..., query=...)
  2. Tasks are detection, referring, point, count_box, count_point, ocr, ocr_grounding, segmentation and matting
  3. A None answer means the target isn't in the image. Treat it as a result, not an error
  4. mask_decoder.pt is a pickle. Load it only from the tencent repository, and check its SHA-256 against the Hub's
  5. Send one image a turn. Video grids are rejected by the decoder
  6. The card says it isn't for identifying individuals or for high-impact decisions on its own

Questions

Which is better for AI agents, Laguna XS 2.1 or WeVisOne-VL-4B?

Laguna XS 2.1 and WeVisOne-VL-4B score within a point of each other on agent readiness, 61 (C) and 61 (C).

Other comparisons with Laguna XS 2.1 or WeVisOne-VL-4B

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