Laguna-M.1
By poolside. 225.8 billion parameters, a context window of 262,144 tokens and the licence apache-2.0.
Facts
- Released
- 2026-06-15 the day the repository was first published on Hugging Face Hugging Face, read
- Licence
- apache-2.0 the licence the model card declares Hugging Face, read
- Open weights
- Yes the weights are published in this Hugging Face repository Hugging Face, read
- Parameters
- 225.8 billion counted from the safetensors weight files Hugging Face, read
- Active parameters
- 14.4 billion estimate estimated from the expert counts and sizes in the configuration model configuration, read
- Knowledge cutoff
- Unknown
- Context window
- 262,144 tokens the maximum position embeddings in the model configuration model configuration, read
- Longest output
- Unknown
- Tool calling
- Unknown
- Structured output
- Unknown
- Reasoning controls
- Unknown
- Inputs and outputs
- text in, text out Hugging Face, read
- Good for
- No source names a use.
Prices
| Provider | Input | Output | Context | As of | Source |
|---|---|---|---|---|---|
| Poolside direct | 0 USD | 0 USD | 262,144 | older than 30 days; check the provider | models.dev, read |
Run it on your own hardware
Weights are the sizes of the files a source lists, or an estimate from the parameter count where none does. Memory is an estimate: weights plus KV cache plus 512 MiB and 5 percent of the weights for runtime buffers. Check it against your hardware.
| Quantization | Weights | Memory at 8,192 tokens | Memory at 32,768 tokens |
|---|---|---|---|
| IQ2_XS | 63.1 GiB | 68.9 GiB | 75.5 GiB |
| IQ2_S | 63.1 GiB | 68.9 GiB | 75.5 GiB |
| IQ2_M | 69.5 GiB | 75.6 GiB | 82.2 GiB |
| Q2_K | 77.7 GiB | 84.2 GiB | 90.8 GiB |
| IQ3_XXS | 82.0 GiB | 88.8 GiB | 95.3 GiB |
| IQ3_S | 91.8 GiB | 99.1 GiB | 106 GiB |
| Q3_K_S | 91.8 GiB | 99.1 GiB | 106 GiB |
| Q3_K_M | 101 GiB | 109 GiB | 115 GiB |
| IQ4_XS | 113 GiB | 121 GiB | 128 GiB |
| IQ4_NL | 119 GiB | 128 GiB | 134 GiB |
| Q4_K_S | 120 GiB | 129 GiB | 135 GiB |
| Q4_K_M | 127 GiB | 136 GiB | 143 GiB |
| Q5_K_S | 145 GiB | 155 GiB | 162 GiB |
| Q5_K_M | 149 GiB | 159 GiB | 166 GiB |
| Q6_K | 173 GiB | 184 GiB | 191 GiB |
| Q8_0 | 224 GiB | 237 GiB | 244 GiB |
| BF16 | 421 GiB | 444 GiB | 451 GiB |
Start it with a local runtime
- Ollama
ollama run hf.co/sigargv/Laguna-M.1-GGUF:Q4_K_S - LM Studio
lms get sigargv/Laguna-M.1-GGUF lms server start - llama.cpp server
llama-server -hf sigargv/Laguna-M.1-GGUF:Q4_K_S --jinja - vLLM
vllm serve poolside/Laguna-M.1 - SGLang
sglang serve --model-path poolside/Laguna-M.1 --port 30000
Use it from your harness
Set up for Poolside with the model poolside/laguna-m.1. Each endpoint page has the same setup for its own address.
OpenCode
Put this in opencode.json in your project folder:
{
"$schema": "https://opencode.ai/config.json",
"provider": {
"poolside": {
"npm": "@ai-sdk/openai-compatible",
"name": "Poolside",
"options": {
"baseURL": "https://inference.poolside.ai/v1",
"apiKey": "{env:POOLSIDE_API_KEY}"
},
"models": {
"poolside/laguna-m.1": {
"name": "Laguna-M.1"
}
}
}
}
}- OpenCode reads any OpenAI-compatible address through the @ai-sdk/openai-compatible package, and an address that speaks the Responses API through @ai-sdk/openai.
From OpenCode documentation, read .
Pi
Put this in ~/.pi/agent/models.json:
{
"providers": {
"poolside": {
"baseUrl": "https://inference.poolside.ai/v1",
"api": "openai-completions",
"apiKey": "$POOLSIDE_API_KEY",
"models": [
{
"id": "poolside/laguna-m.1"
}
]
}
}
}- The apiKey field can name an environment variable as $NAME.
From Pi documentation, read .
Codex
Codex speaks only the Responses API, and Poolside documents no Responses address. A gateway that offers one can sit in between.
- Codex speaks the Responses API only: responses is the one supported wire API of a custom provider. Ollama and LM Studio are built in and start with --oss.
From Codex documentation, read .
Claude Code
Claude Code sends Anthropic Messages requests, and Poolside documents no such address. A gateway that translates to that API can sit in between.
- Claude Code sends Anthropic Messages requests to ANTHROPIC_BASE_URL. Anthropic says it does not support routing Claude Code to models other than Claude through any gateway, so some features may not work with another model.
From Claude Code documentation, read .
Other ways to reach it
- Ollama, model
hf.co/sigargv/Laguna-M.1-GGUF:Q4_K_S
Published results
These are results other people published. Baltor did not run them and does not rank models by them.
- Results the maker published on the model card published by poolside Hugging Face, read
Sources of this page
Paid links
No link in this directory is a paid link or an ad, and no listing is paid for. The order and the contents of every list come from the sources named on this page.