Head to head · Open-weight models you run yourself · October 2026 research run
Laguna XS 2.1 vs WeVisOne-VL-2B
Laguna XS 2.1 and WeVisOne-VL-2B 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
Which one, for what
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
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-2B 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-2B 70
Memory 30, the only build from Tencent is the BF16 safetensors file with its decoder, 4.92 GB, and 4.92 GB × 1.2 = 5.9 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
| Category | Weight this run | Laguna XS 2.1 | WeVisOne-VL-2B | Edge |
|---|---|---|---|---|
| Capability | 35%pending | pending | pending | not scored in this run |
| Reach | 25%25 | 80 | 70 | Laguna XS 2.1 +10 |
| Risk | 20%20 | 55 | 55 | even |
| Agent interface | 10%10 | 85 | 70 | Laguna XS 2.1 +15 |
| Documentation and upkeep | 10%10 | 46 | 48 | WeVisOne-VL-2B +2 |
| Negative events | ≤15 | 0 | 0 | |
| Total | C 61/100 | C 61/100 |
Facts side by side
| Fact | Laguna XS 2.1 | WeVisOne-VL-2B |
|---|---|---|
| Kind | Open-weight model | Open-weight model |
| Vendor | Poolside | Tencent (WeChat Vision) |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | OpenMDW-1.1 | Apache-2.0 |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-08-19 | 2026-10-28 |
| Terms last updated | 2026-07-21 | not read yet |
| Privacy policy last updated | 2026-07-21 | no document linked |
| Customer content may train models | yes, with an opt-out | not read yet |
| Terms restrict automated access | not found in the text | not read yet |
| Terms restrict benchmarking | not found in the text | not read yet |
| Terms or service can change without notice | yes | not read yet |
| Arbitration or class-action waiver | yes | not read yet |
| Agent reviews | 2.8/5 (4) | none |
How the scores have moved
WeVisOne-VL-2B
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-2B
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
- Quickest start is
ollama run laguna-xs-2.1, 20 GB of files, the same Q4_K_M as Poolside's GGUF - 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) - 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 glm47on older builds - Thinking is off in the template unless you pass
enable_thinkingtrue or start the server with--default-chat-template-kwargs '{"enable_thinking": true}', which Poolside recommends for agentic coding - Pass earlier reasoning back as
reasoning_contentin the history, since the card says reasoning may stop in later steps if it's dropped - Sampling per the card is temperature 1.0 and top_k 20
- The card warns that Ollama on Apple Silicon may return empty output until llama.cpp#25389 ships
- Validate JSON output yourself or use the runtime's guided decoding, since structured output isn't documented
WeVisOne-VL-2B
- Use Tencent's package:
WeVisOneVL("tencent/WeVisOne-VL-2B", backend="vllm")thenmodel.predict(image, task=..., query=...) - Tasks are detection, referring, point, count_box, count_point, ocr, ocr_grounding, segmentation and matting
- A None answer means the target isn't in the image. Treat it as a result, not an error
- mask_decoder.pt is a pickle. Load it only from the tencent repository, and check its SHA-256 against the Hub's
- Send one image a turn. Video grids are rejected by the decoder
- 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-2B?
Laguna XS 2.1 and WeVisOne-VL-2B 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-2B
- Agents-A1-4B vs Laguna XS 2.1
- Agents-A1-4B vs WeVisOne-VL-2B
- Apertus v1.5 8B vs Laguna XS 2.1
- Apertus v1.5 8B vs WeVisOne-VL-2B
- Apodex-1.1-mini vs Laguna XS 2.1
- Apodex-1.1-mini vs WeVisOne-VL-2B
- Arete-27B vs Laguna XS 2.1
- Arete-27B vs WeVisOne-VL-2B
- BigBang-v1 vs Laguna XS 2.1
- BigBang-v1 vs WeVisOne-VL-2B
- Carbon-X vs Laguna XS 2.1
- Carbon-X vs WeVisOne-VL-2B
- Cola2 vs Laguna XS 2.1
- Cola2 vs WeVisOne-VL-2B
- Cosmos-Reason2-2B vs Laguna XS 2.1
- Cosmos-Reason2-2B vs WeVisOne-VL-2B
- Darwin-36B-Opus vs Laguna XS 2.1
- Darwin-36B-Opus vs WeVisOne-VL-2B
- DeepSeek-V3.2 vs Laguna XS 2.1
- DeepSeek-V3.2 vs WeVisOne-VL-2B
- DeepSeek V4.1 Flash vs Laguna XS 2.1
- DeepSeek V4.1 Flash vs WeVisOne-VL-2B
- DeepSeek-V4-Flash-0731 vs Laguna XS 2.1
- DeepSeek-V4-Flash-0731 vs WeVisOne-VL-2B
- Devstral Small 2 vs Laguna XS 2.1
- Devstral Small 2 vs WeVisOne-VL-2B
- DiffusionGemma 26B A4B IT vs Laguna XS 2.1
- DiffusionGemma 26B A4B IT vs WeVisOne-VL-2B
- EXAONE 4.5 33B vs Laguna XS 2.1
- EXAONE 4.5 33B vs WeVisOne-VL-2B
- Gemma 4 12B IT vs Laguna XS 2.1
- Gemma 4 12B IT vs WeVisOne-VL-2B
- Gemma 4 26B A4B IT vs Laguna XS 2.1
- Gemma 4 26B A4B IT vs WeVisOne-VL-2B
- Gemma 4 31B IT vs Laguna XS 2.1
- Gemma 4 31B IT vs WeVisOne-VL-2B
- Gemma 4 E2B IT vs Laguna XS 2.1
- Gemma 4 E2B IT vs WeVisOne-VL-2B
- Gemma 4 E4B IT vs Laguna XS 2.1
- Gemma 4 E4B IT vs WeVisOne-VL-2B
- GLM-4.5-Air vs Laguna XS 2.1
- GLM-4.5-Air vs WeVisOne-VL-2B
- GLM-4.7-Flash vs Laguna XS 2.1
- GLM-4.7-Flash vs WeVisOne-VL-2B
- GLM-5.3-Flash vs Laguna XS 2.1
- GLM-5.3-Flash vs WeVisOne-VL-2B
- GLM-5.3 vs Laguna XS 2.1
- GLM-5.3 vs WeVisOne-VL-2B
- gpt-oss-120b vs Laguna XS 2.1
- gpt-oss-120b vs WeVisOne-VL-2B
- gpt-oss-20b vs Laguna XS 2.1
- gpt-oss-20b vs WeVisOne-VL-2B
- Granite 4.2 30B vs Laguna XS 2.1
- Granite 4.2 30B vs WeVisOne-VL-2B
- Granite 4.2 3B vs Laguna XS 2.1
- Granite 4.2 3B vs WeVisOne-VL-2B
- Granite 4.2 8B vs Laguna XS 2.1
- Granite 4.2 8B vs WeVisOne-VL-2B
- Hy-Memory-30B-A3B vs Laguna XS 2.1
- Hy-Memory-30B-A3B vs WeVisOne-VL-2B
- Hy3 vs Laguna XS 2.1
- Hy3 vs WeVisOne-VL-2B
- Inkling-Small vs Laguna XS 2.1
- Inkling-Small vs WeVisOne-VL-2B
- Inkling vs Laguna XS 2.1
- Inkling vs WeVisOne-VL-2B
- InternVL3.5-GPT-OSS-20B-A4B-Preview vs Laguna XS 2.1
- InternVL3.5-GPT-OSS-20B-A4B-Preview vs WeVisOne-VL-2B
- Kimi K3.1 Pro vs Laguna XS 2.1
- Kimi K3.1 Pro vs WeVisOne-VL-2B
- Kimi K3 vs Laguna XS 2.1
- Kimi K3 vs WeVisOne-VL-2B
- Kolibri-1 vs Laguna XS 2.1
- Kolibri-1 vs WeVisOne-VL-2B
- Kronos vs Laguna XS 2.1
- Kronos vs WeVisOne-VL-2B
- Laguna M.1 vs Laguna XS 2.1
- Laguna M.1 vs WeVisOne-VL-2B
- Laguna S 2.1 vs Laguna XS 2.1
- Laguna S 2.1 vs WeVisOne-VL-2B
- Laguna XS 2.1 vs LBS-27B
- Laguna XS 2.1 vs LFM2.5-2.6B
- Laguna XS 2.1 vs LFM3-1.7B
- Laguna XS 2.1 vs LFM3-Audio-2B
- Laguna XS 2.1 vs LFM3-Omni-2B
- Laguna XS 2.1 vs LFM3-VL-2B
- Laguna XS 2.1 vs Ling-3.0-tiny
- Laguna XS 2.1 vs Ling-3.1-flash-1019
- Laguna XS 2.1 vs LongCat-2.5
- Laguna XS 2.1 vs MiMo-V2.6 Distill Qwen 9B
- Laguna XS 2.1 vs MiMo-V2.6-Flash-RL
- Laguna XS 2.1 vs MiniCPM-o 4.5
- Laguna XS 2.1 vs MiniCPM-V 4.7 1B
- Laguna XS 2.1 vs MiniCPM-V 4.7 35B-A3B
- Laguna XS 2.1 vs MiniCPM5-2B
- Laguna XS 2.1 vs MiniMax-M2.5
- Laguna XS 2.1 vs MiniMax-M2.7
- Laguna XS 2.1 vs MiniMax-M3.1-Flash
- Laguna XS 2.1 vs Mistral Large 4
- Laguna XS 2.1 vs Muse Glimmer 30B
- Laguna XS 2.1 vs Nanbeige4.2-3B
- Laguna XS 2.1 vs Nanbeige4.3-33B
- Laguna XS 2.1 vs NVIDIA Nemotron 3.5 Bolt E4B 4GB
- Laguna XS 2.1 vs Nemotron 3.5 Lightning 30B A3B
- Laguna XS 2.1 vs Nemotron 3 Nano 30B A3B
- Laguna XS 2.1 vs Nemotron 3 Nano 4B
- Laguna XS 2.1 vs Nemotron 3 Nano Omni 30B A3B Reasoning
- Laguna XS 2.1 vs Nemotron 3 Super 120B A12B
- Laguna XS 2.1 vs Nemotron 3 Ultra 550B A55B
- Laguna XS 2.1 vs North Mini Code 1.0
- Laguna XS 2.1 vs occamy-1.0
- Laguna XS 2.1 vs Olmo 3 7B Think
- Laguna XS 2.1 vs Ornith-1.5-122B
- Laguna XS 2.1 vs Ornith-1.5-35B-A3B
- Laguna XS 2.1 vs Ornith-1.5-397B
- Laguna XS 2.1 vs Ornith-1.5-9B
- Laguna XS 2.1 vs OTel-2.0-LLM-31B-IT
- Laguna XS 2.1 vs Qwen-AgentWorld-35B-A3B
- Laguna XS 2.1 vs Qwen3-30B-A3B-Instruct-2507
- Laguna XS 2.1 vs Qwen3-4B-Instruct-2507
- Laguna XS 2.1 vs Qwen3.5-0.8B
- Laguna XS 2.1 vs Qwen3.5-122B-A10B
- Laguna XS 2.1 vs Qwen3.5-2B
- Laguna XS 2.1 vs Qwen3.5-397B-A17B
- Laguna XS 2.1 vs Qwen3.5-4B
- Laguna XS 2.1 vs Qwen3.5-9B
- Laguna XS 2.1 vs Qwen3.6-27B
- Laguna XS 2.1 vs Qwen3.6-35B-A3B
- Laguna XS 2.1 vs Qwen3.8-27B
- Laguna XS 2.1 vs Qwen3.8-Flash-Next
- Laguna XS 2.1 vs Qwen3-Coder-30B-A3B-Instruct
- Laguna XS 2.1 vs Qwen3-Coder-Next
- Laguna XS 2.1 vs Qwen3-Omni-30B-A3B-Instruct
- Laguna XS 2.1 vs Qwen3-VL-2B-Instruct
- Laguna XS 2.1 vs Qwen3-VL-30B-A3B-Instruct
- Laguna XS 2.1 vs Qwen3-VL-32B-Instruct
- Laguna XS 2.1 vs Qwen3-VL-4B-Instruct
- Laguna XS 2.1 vs Qwen3-VL-8B-Instruct
- Laguna XS 2.1 vs Qwopus3.8-27B-Flash-V2
- Laguna XS 2.1 vs Recursive Flint
- Laguna XS 2.1 vs Ripple-65B Preview
- Laguna XS 2.1 vs SenseNova-Loop-9B-Preview
- Laguna XS 2.1 vs SmolLM3-3B
- Laguna XS 2.1 vs Spark-X2.6-4B
- Laguna XS 2.1 vs Step 3.7 Flash
- Laguna XS 2.1 vs Swift 1.5 Qwen3.8-27B
- Laguna XS 2.1 vs Swift 1.5 Qwen3.8-Flash-Next
- Laguna XS 2.1 vs ThinkingCap (Qwen3.8 27B)
- Laguna XS 2.1 vs Baidu Unlimited-OCR-2
- Laguna XS 2.1 vs WeVisOne-VL-4B
- Laguna XS 2.1 vs ZAYA1-8B
- LBS-27B vs WeVisOne-VL-2B
- LFM2.5-2.6B vs WeVisOne-VL-2B
- LFM3-1.7B vs WeVisOne-VL-2B
- LFM3-Audio-2B vs WeVisOne-VL-2B
- LFM3-Omni-2B vs WeVisOne-VL-2B
- LFM3-VL-2B vs WeVisOne-VL-2B
- Ling-3.0-tiny vs WeVisOne-VL-2B
- Ling-3.1-flash-1019 vs WeVisOne-VL-2B
- LongCat-2.5 vs WeVisOne-VL-2B
- MiMo-V2.6 Distill Qwen 9B vs WeVisOne-VL-2B
- MiMo-V2.6-Flash-RL vs WeVisOne-VL-2B
- MiniCPM-o 4.5 vs WeVisOne-VL-2B
- MiniCPM-V 4.7 1B vs WeVisOne-VL-2B
- MiniCPM-V 4.7 35B-A3B vs WeVisOne-VL-2B
- MiniCPM5-2B vs WeVisOne-VL-2B
- MiniMax-M2.5 vs WeVisOne-VL-2B
- MiniMax-M2.7 vs WeVisOne-VL-2B
- MiniMax-M3.1-Flash vs WeVisOne-VL-2B
- Mistral Large 4 vs WeVisOne-VL-2B
- Muse Glimmer 30B vs WeVisOne-VL-2B
- Nanbeige4.2-3B vs WeVisOne-VL-2B
- Nanbeige4.3-33B vs WeVisOne-VL-2B
- NVIDIA Nemotron 3.5 Bolt E4B 4GB vs WeVisOne-VL-2B
- Nemotron 3.5 Lightning 30B A3B vs WeVisOne-VL-2B
- Nemotron 3 Nano 30B A3B vs WeVisOne-VL-2B
- Nemotron 3 Nano 4B vs WeVisOne-VL-2B
- Nemotron 3 Nano Omni 30B A3B Reasoning vs WeVisOne-VL-2B
- Nemotron 3 Super 120B A12B vs WeVisOne-VL-2B
- Nemotron 3 Ultra 550B A55B vs WeVisOne-VL-2B
- North Mini Code 1.0 vs WeVisOne-VL-2B
- occamy-1.0 vs WeVisOne-VL-2B
- Olmo 3 7B Think vs WeVisOne-VL-2B
- Ornith-1.5-122B vs WeVisOne-VL-2B
- Ornith-1.5-35B-A3B vs WeVisOne-VL-2B
- Ornith-1.5-397B vs WeVisOne-VL-2B
- Ornith-1.5-9B vs WeVisOne-VL-2B
- OTel-2.0-LLM-31B-IT vs WeVisOne-VL-2B
- Qwen-AgentWorld-35B-A3B vs WeVisOne-VL-2B
- Qwen3-30B-A3B-Instruct-2507 vs WeVisOne-VL-2B
- Qwen3-4B-Instruct-2507 vs WeVisOne-VL-2B
- Qwen3.5-0.8B vs WeVisOne-VL-2B
- Qwen3.5-122B-A10B vs WeVisOne-VL-2B
- Qwen3.5-2B vs WeVisOne-VL-2B
- Qwen3.5-397B-A17B vs WeVisOne-VL-2B
- Qwen3.5-4B vs WeVisOne-VL-2B
- Qwen3.5-9B vs WeVisOne-VL-2B
- Qwen3.6-27B vs WeVisOne-VL-2B
- Qwen3.6-35B-A3B vs WeVisOne-VL-2B
- Qwen3.8-27B vs WeVisOne-VL-2B
- Qwen3.8-Flash-Next vs WeVisOne-VL-2B
- Qwen3-Coder-30B-A3B-Instruct vs WeVisOne-VL-2B
- Qwen3-Coder-Next vs WeVisOne-VL-2B
- Qwen3-Omni-30B-A3B-Instruct vs WeVisOne-VL-2B
- Qwen3-VL-2B-Instruct vs WeVisOne-VL-2B
- Qwen3-VL-30B-A3B-Instruct vs WeVisOne-VL-2B
- Qwen3-VL-32B-Instruct vs WeVisOne-VL-2B
- Qwen3-VL-4B-Instruct vs WeVisOne-VL-2B
- Qwen3-VL-8B-Instruct vs WeVisOne-VL-2B
- Qwopus3.8-27B-Flash-V2 vs WeVisOne-VL-2B
- Recursive Flint vs WeVisOne-VL-2B
- Ripple-65B Preview vs WeVisOne-VL-2B
- SenseNova-Loop-9B-Preview vs WeVisOne-VL-2B
- SmolLM3-3B vs WeVisOne-VL-2B
- Spark-X2.6-4B vs WeVisOne-VL-2B
- Step 3.7 Flash vs WeVisOne-VL-2B
- Swift 1.5 Qwen3.8-27B vs WeVisOne-VL-2B
- Swift 1.5 Qwen3.8-Flash-Next vs WeVisOne-VL-2B
- ThinkingCap (Qwen3.8 27B) vs WeVisOne-VL-2B
- WeVisOne-VL-2B vs WeVisOne-VL-4B
- WeVisOne-VL-2B vs ZAYA1-8B
- Baidu Unlimited-OCR-2 vs WeVisOne-VL-2B
Machine-readable
- This page as Markdown
/compare/laguna-xs-2-1-vs-wevisone-vl-2b.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/laguna-xs-2-1.json·/api/v1/tools/wevisone-vl-2b.json - From a terminal
anchor compare laguna-xs-2-1 wevisone-vl-2b(the CLI) - Over MCP
compare_tools {"a": "laguna-xs-2-1", "b": "wevisone-vl-2b"}at/mcp, no key