- Size
- 33.4B parameterscounted from the safetensors header on the Hub
- Licence
- unknown, Apache License 2.0Our reading, check the licence: You can use, change and redistribute the model, including commercially. Keep the licence and any notices, and say which files you changed; you do not have to publish your changes. It includes a patent licence that ends for anyone who sues over patents in the work.
- On the Hub since
- 23 Apr 2026the date the repo was created
- Context length
- 256k tokensfrom the model's config
- Kind
- Base model (no base model declared on the Hub)LagunaForCausalLM
- On Hugging Face
- poolside/Laguna-XS.2686k downloads in the last 30 days, 320 likes
Scores
- default setting0.0%vals.ai
Epoch's name: laguna-xs.2. Best closed model on this set: claude-fable-5-1_max, 100.0% (Anthropic). All 85 results
Claimed by the maker Claimed
The model card has no claimed scores in a machine-readable form (the card's model-index), so none are shown. The maker may give scores in the card text: read the card.
Other views, which we link to and do not copy: look this model up on Artificial Analysis and the Arena leaderboard.
Independent scores from Epoch AI (CC-BY 4.0), fetched 19 Nov 2026: Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from ‘https://epoch.ai/benchmarks’ [online resource]. Each row links its own source. What the badges mean.
Run it yourself
Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 0.37 GB, worked out from the model's config (poolside/Laguna-XS.2), at 16-bit precision. Choose a machine above to see a verdict for each format. Method
GGUF for llama.cpp, Ollama, LM Studio and others
Lucebox/Laguna-XS.2-GGUF (converted by Lucebox), 232 downloads. Sizes are the real files on the Hub, all parts added up.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| Q4_K_M | 18.9 GBfile size | 19.8 GB18.9 + 0.37 + 0.50 | Commandsllama.cpp llama-server -hf Lucebox/Laguna-XS.2-GGUF:Q4_K_MOllama ollama run hf.co/Lucebox/Laguna-XS.2-GGUF:Q4_K_MDownload hf download Lucebox/Laguna-XS.2-GGUF --include "laguna-xs2-Q4_K_M.gguf" --local-dir Laguna-XS.2-GGUF |
| BF16 | 62.3 GBfile size | 63.2 GB62.3 + 0.37 + 0.50 | Commandsllama.cpp llama-server -hf Lucebox/Laguna-XS.2-GGUF:BF16Ollama ollama run hf.co/Lucebox/Laguna-XS.2-GGUF:BF16Download hf download Lucebox/Laguna-XS.2-GGUF --include "laguna-xs2-bf16.gguf" --local-dir Laguna-XS.2-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| MLXmanjunathshiva/Laguna-XS.2-tq3-g64 | 13.8 GBfile size | 14.7 GB13.8 + 0.37 + 0.50 | Download page |
| MLX 4bitmlx-community/Laguna-XS.2-4bit | 17.5 GBfile size | 18.4 GB17.5 + 0.37 + 0.50 | Download page |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| BF16original weights | 62.3 GBfile size | 63.2 GB62.3 + 0.37 + 0.50 |
hf download poolside/Laguna-XS.2 --local-dir Laguna-XS.2Other conversions (5; sizes not read)
- poolside/Laguna-XS.2-FP8 FP8, by the maker, 440 downloads
- poolside/Laguna-XS.2-NVFP4 NVFP4, by the maker, 358 downloads
- poolside/Laguna-XS.2-INT4 Other, int4, by the maker, 272 downloads
- cyankiwi/Laguna-XS.2-AWQ-INT4 AWQ, int4, 2.4k downloads
- poolside-laguna-hackathon/Laguna-XS.2-GGUF GGUF, 119 downloads; sizes not used: file sizes do not match this model's 33.4B parameters (median 2.20 times the nominal size); the repo may be tagged wrongly
The Hub tags 16 quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.
Run it by API
No provider on Hugging Face Inference Providers serves this model (as of 19 Nov 2026, 13:58 UTC). Other hosts may; we only list what the router reports.
Not built yet: one key for every open model, with BlockRun, and our own tested-quality score per provider. Until then, precision and measured speed are the best guide to a provider here.
Planned for this page Not built yet
- Try it in private chat
- A link to Solana AI's confidential chat for the models it serves. This model is not listed as served there.
- Fine-tune it
- Fine-tuning a few base models from this page and publishing the result here.
- Creators and earnings
- Pages for people who publish fine-tunes and adapters of this model, and what they earn.
- Fund and bounties
- Bounties for new open models, paid from a public fund. How the fund will work.
- Contribute compute
- How to give compute to open model work, with Akash.
Model data from the Hugging Face Hub 19 Nov 2026, 13:43 UTC. The repo. Found a mistake on this page? Tell us.