Head to head · Open-weight models you run yourself · October 2026 research run
Laguna XS 2.1 vs ZAYA1-8B
Laguna XS 2.1 and ZAYA1-8B 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
- Agent interface, 85 against 60
Watch for
No reply from Poolside to any discussion, including reports about the tokenizer and remote code
ZAYA1-8B C
Best for People who want a small, fast reasoning model for maths and code and can live without tool calling
No category where it leads by five points or more, and no fact that sets it apart.
Watch for
Tool calling needs a parser that only Zyphra's vLLM fork has
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 +25
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.
ZAYA1-8B 60
Chat template 20, chat_template.jinja in the repository (10,700 characters). Tool-calling format 10, only the template and a fork say it. Trained tool calling 10, the template takes tools and renders calls, and the card recommends settings for agent use, but it doesn't say the model was trained for tool calling or for several calls in a turn, so the lower band. Structured output 0, Nothing on the card about JSON or schema-constrained output. Reasoning control 10, the template has an enable_thinking switch, and the card names the qwen3 reasoning parser, which returns the reasoning apart from the answer. Context 10, 131,072 positions in config.json, for an architecture Zyphra trained end to end, so the config is the model's own. 20 + 10 + 10 + 0 + 10 + 10 = 60.
Score by category
| Category | Weight this run | Laguna XS 2.1 | ZAYA1-8B | Edge |
|---|---|---|---|---|
| Capability | 35%pending | pending | pending | not scored in this run |
| Reach | 25%25 | 80 | 80 | even |
| Risk | 20%20 | 55 | 55 | even |
| Agent interface | 10%10 | 85 | 60 | Laguna XS 2.1 +25 |
| Documentation and upkeep | 10%10 | 46 | 50 | ZAYA1-8B +4 |
| Negative events | ≤15 | 0 | 0 | |
| Total | C 61/100 | C 61/100 |
Facts side by side
| Fact | Laguna XS 2.1 | ZAYA1-8B |
|---|---|---|
| Kind | Open-weight model | Open-weight model |
| Vendor | Poolside | Zyphra |
| 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 | 2026-07-02 |
| Terms last updated | 2026-07-21 | no document linked |
| 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
ZAYA1-8B
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.
ZAYA1-8B
A small reasoning model trained from scratch by one lab, with a clean licence, 4-bit and FP8 builds and a team that answers questions. It's the hardest of the small models to run: its own architecture, a card that points at forks, and tool calling that needs a parser no release has. Little on limits, data or safety.
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
ZAYA1-8B
- Use it for reasoning, maths and code. Don't count on tool calling outside Zyphra's vLLM fork
- Run it with Transformers 5.22.2 or SGLang 0.5.23, which have the model built in
- Use temperature 1.0 and top_p 0.95 in general, and temperature 0.6 for agent and code work
- Download
Zyphra/ZAYA1-8B, not the legacy repository, for the released runtimes - The quantised repositories have no licence tag. The main one is Apache 2.0
Questions
Which is better for AI agents, Laguna XS 2.1 or ZAYA1-8B?
Laguna XS 2.1 and ZAYA1-8B score within a point of each other on agent readiness, 61 (C) and 61 (C).
Other comparisons with Laguna XS 2.1 or ZAYA1-8B
- Agents-A1-4B vs Laguna XS 2.1
- Agents-A1-4B vs ZAYA1-8B
- Apertus v1.5 8B vs Laguna XS 2.1
- Apertus v1.5 8B vs ZAYA1-8B
- Apodex-1.1-mini vs Laguna XS 2.1
- Apodex-1.1-mini vs ZAYA1-8B
- Arete-27B vs Laguna XS 2.1
- Arete-27B vs ZAYA1-8B
- BigBang-v1 vs Laguna XS 2.1
- BigBang-v1 vs ZAYA1-8B
- Carbon-X vs Laguna XS 2.1
- Carbon-X vs ZAYA1-8B
- Cola2 vs Laguna XS 2.1
- Cola2 vs ZAYA1-8B
- Cosmos-Reason2-2B vs Laguna XS 2.1
- Cosmos-Reason2-2B vs ZAYA1-8B
- Darwin-36B-Opus vs Laguna XS 2.1
- Darwin-36B-Opus vs ZAYA1-8B
- DeepSeek-V3.2 vs Laguna XS 2.1
- DeepSeek-V3.2 vs ZAYA1-8B
- DeepSeek V4.1 Flash vs Laguna XS 2.1
- DeepSeek V4.1 Flash vs ZAYA1-8B
- DeepSeek-V4-Flash-0731 vs Laguna XS 2.1
- DeepSeek-V4-Flash-0731 vs ZAYA1-8B
- Devstral Small 2 vs Laguna XS 2.1
- Devstral Small 2 vs ZAYA1-8B
- DiffusionGemma 26B A4B IT vs Laguna XS 2.1
- DiffusionGemma 26B A4B IT vs ZAYA1-8B
- EXAONE 4.5 33B vs Laguna XS 2.1
- EXAONE 4.5 33B vs ZAYA1-8B
- Gemma 4 12B IT vs Laguna XS 2.1
- Gemma 4 12B IT vs ZAYA1-8B
- Gemma 4 26B A4B IT vs Laguna XS 2.1
- Gemma 4 26B A4B IT vs ZAYA1-8B
- Gemma 4 31B IT vs Laguna XS 2.1
- Gemma 4 31B IT vs ZAYA1-8B
- Gemma 4 E2B IT vs Laguna XS 2.1
- Gemma 4 E2B IT vs ZAYA1-8B
- Gemma 4 E4B IT vs Laguna XS 2.1
- Gemma 4 E4B IT vs ZAYA1-8B
- GLM-4.5-Air vs Laguna XS 2.1
- GLM-4.5-Air vs ZAYA1-8B
- GLM-4.7-Flash vs Laguna XS 2.1
- GLM-4.7-Flash vs ZAYA1-8B
- GLM-5.3-Flash vs Laguna XS 2.1
- GLM-5.3-Flash vs ZAYA1-8B
- GLM-5.3 vs Laguna XS 2.1
- GLM-5.3 vs ZAYA1-8B
- gpt-oss-120b vs Laguna XS 2.1
- gpt-oss-120b vs ZAYA1-8B
- gpt-oss-20b vs Laguna XS 2.1
- gpt-oss-20b vs ZAYA1-8B
- Granite 4.2 30B vs Laguna XS 2.1
- Granite 4.2 30B vs ZAYA1-8B
- Granite 4.2 3B vs Laguna XS 2.1
- Granite 4.2 3B vs ZAYA1-8B
- Granite 4.2 8B vs Laguna XS 2.1
- Granite 4.2 8B vs ZAYA1-8B
- Hy-Memory-30B-A3B vs Laguna XS 2.1
- Hy-Memory-30B-A3B vs ZAYA1-8B
- Hy3 vs Laguna XS 2.1
- Hy3 vs ZAYA1-8B
- Inkling-Small vs Laguna XS 2.1
- Inkling-Small vs ZAYA1-8B
- Inkling vs Laguna XS 2.1
- Inkling vs ZAYA1-8B
- InternVL3.5-GPT-OSS-20B-A4B-Preview vs Laguna XS 2.1
- InternVL3.5-GPT-OSS-20B-A4B-Preview vs ZAYA1-8B
- Kimi K3.1 Pro vs Laguna XS 2.1
- Kimi K3.1 Pro vs ZAYA1-8B
- Kimi K3 vs Laguna XS 2.1
- Kimi K3 vs ZAYA1-8B
- Kolibri-1 vs Laguna XS 2.1
- Kolibri-1 vs ZAYA1-8B
- Kronos vs Laguna XS 2.1
- Kronos vs ZAYA1-8B
- Laguna M.1 vs Laguna XS 2.1
- Laguna M.1 vs ZAYA1-8B
- Laguna S 2.1 vs Laguna XS 2.1
- Laguna S 2.1 vs ZAYA1-8B
- 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-2B
- Laguna XS 2.1 vs WeVisOne-VL-4B
- LBS-27B vs ZAYA1-8B
- LFM2.5-2.6B vs ZAYA1-8B
- LFM3-1.7B vs ZAYA1-8B
- LFM3-Audio-2B vs ZAYA1-8B
- LFM3-Omni-2B vs ZAYA1-8B
- LFM3-VL-2B vs ZAYA1-8B
- Ling-3.0-tiny vs ZAYA1-8B
- Ling-3.1-flash-1019 vs ZAYA1-8B
- LongCat-2.5 vs ZAYA1-8B
- MiMo-V2.6 Distill Qwen 9B vs ZAYA1-8B
- MiMo-V2.6-Flash-RL vs ZAYA1-8B
- MiniCPM-o 4.5 vs ZAYA1-8B
- MiniCPM-V 4.7 1B vs ZAYA1-8B
- MiniCPM-V 4.7 35B-A3B vs ZAYA1-8B
- MiniCPM5-2B vs ZAYA1-8B
- MiniMax-M2.5 vs ZAYA1-8B
- MiniMax-M2.7 vs ZAYA1-8B
- MiniMax-M3.1-Flash vs ZAYA1-8B
- Mistral Large 4 vs ZAYA1-8B
- Muse Glimmer 30B vs ZAYA1-8B
- Nanbeige4.2-3B vs ZAYA1-8B
- Nanbeige4.3-33B vs ZAYA1-8B
- NVIDIA Nemotron 3.5 Bolt E4B 4GB vs ZAYA1-8B
- Nemotron 3.5 Lightning 30B A3B vs ZAYA1-8B
- Nemotron 3 Nano 30B A3B vs ZAYA1-8B
- Nemotron 3 Nano 4B vs ZAYA1-8B
- Nemotron 3 Nano Omni 30B A3B Reasoning vs ZAYA1-8B
- Nemotron 3 Super 120B A12B vs ZAYA1-8B
- Nemotron 3 Ultra 550B A55B vs ZAYA1-8B
- North Mini Code 1.0 vs ZAYA1-8B
- occamy-1.0 vs ZAYA1-8B
- Olmo 3 7B Think vs ZAYA1-8B
- Ornith-1.5-122B vs ZAYA1-8B
- Ornith-1.5-35B-A3B vs ZAYA1-8B
- Ornith-1.5-397B vs ZAYA1-8B
- Ornith-1.5-9B vs ZAYA1-8B
- OTel-2.0-LLM-31B-IT vs ZAYA1-8B
- Qwen-AgentWorld-35B-A3B vs ZAYA1-8B
- Qwen3-30B-A3B-Instruct-2507 vs ZAYA1-8B
- Qwen3-4B-Instruct-2507 vs ZAYA1-8B
- Qwen3.5-0.8B vs ZAYA1-8B
- Qwen3.5-122B-A10B vs ZAYA1-8B
- Qwen3.5-2B vs ZAYA1-8B
- Qwen3.5-397B-A17B vs ZAYA1-8B
- Qwen3.5-4B vs ZAYA1-8B
- Qwen3.5-9B vs ZAYA1-8B
- Qwen3.6-27B vs ZAYA1-8B
- Qwen3.6-35B-A3B vs ZAYA1-8B
- Qwen3.8-27B vs ZAYA1-8B
- Qwen3.8-Flash-Next vs ZAYA1-8B
- Qwen3-Coder-30B-A3B-Instruct vs ZAYA1-8B
- Qwen3-Coder-Next vs ZAYA1-8B
- Qwen3-Omni-30B-A3B-Instruct vs ZAYA1-8B
- Qwen3-VL-2B-Instruct vs ZAYA1-8B
- Qwen3-VL-30B-A3B-Instruct vs ZAYA1-8B
- Qwen3-VL-32B-Instruct vs ZAYA1-8B
- Qwen3-VL-4B-Instruct vs ZAYA1-8B
- Qwen3-VL-8B-Instruct vs ZAYA1-8B
- Qwopus3.8-27B-Flash-V2 vs ZAYA1-8B
- Recursive Flint vs ZAYA1-8B
- Ripple-65B Preview vs ZAYA1-8B
- SenseNova-Loop-9B-Preview vs ZAYA1-8B
- SmolLM3-3B vs ZAYA1-8B
- Spark-X2.6-4B vs ZAYA1-8B
- Step 3.7 Flash vs ZAYA1-8B
- Swift 1.5 Qwen3.8-27B vs ZAYA1-8B
- Swift 1.5 Qwen3.8-Flash-Next vs ZAYA1-8B
- ThinkingCap (Qwen3.8 27B) vs ZAYA1-8B
- Baidu Unlimited-OCR-2 vs ZAYA1-8B
- WeVisOne-VL-2B vs ZAYA1-8B
- WeVisOne-VL-4B vs ZAYA1-8B
Machine-readable
- This page as Markdown
/compare/laguna-xs-2-1-vs-zaya1-8b.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/zaya1-8b.json - From a terminal
anchor compare laguna-xs-2-1 zaya1-8b(the CLI) - Over MCP
compare_tools {"a": "laguna-xs-2-1", "b": "zaya1-8b"}at/mcp, no key