← All models

Laguna S 2.1 (118B-A8B, Q8)

codingOpenMDW 1.1tools

Poolside's Laguna S 2.1, a 118B-parameter Mixture-of-Experts model with about 8B active parameters per token, built for agentic coding and long-horizon software work. It supports native tool calling and interleaved reasoning between tool calls. The official Q8_0 GGUF is about 128GB on disk, while the community MLX 8-bit conversion is about 125GB and runs natively on Apple Silicon. Both target larger-memory workstations; Q6 is the practical Laguna tier for a 128GB Mac. Gezel defaults to Poolside's quality-recommended 256K context window; the underlying checkpoint can be extended to 1M context with explicit YaRN overrides.

At a glance

Parameters
118B
Quantization
Q8_0
Context window
262K tokens
Approx. size
128.0 GB
Engines
llama.cpp, MLX
License
OpenMDW-1.1 (open)
Version
v1.0.0 , released 2026-07-21
Family
glm

Tuning

Defaults a gezel client applies out of the box, from real evaluation runs against this exact quantization.

sampling.temperature
0.7
sampling.topP
0.95
sampling.maxTokens
8192
reasoning.thinkingBudget
4096
reasoning.enableThinking
true
profiles
thinking-general, thinking-coding, thinking-precise, instruct, creative

Model behaviors

Client-side behavior modules the catalog enables for this model (reasoning-tag handling, fabrication detection, prompt shaping).

Sources

llama.cpp (GGUF)
poolside/Laguna-S-2.1-GGUF · laguna-s-2.1-Q8_0.gguf · Q8_0
MLX
Vontra/Laguna-S-2.1-MLX-8bit
Upstream
https://huggingface.co/poolside/Laguna-S-2.1
Manifest
View on GitHub

Tags