MLX 6-bit affine quantization of poolside/Laguna-S-2.1, packaged for Apple Silicon experiments and local OpenAI-compatible serving.
Laguna S 2.1 is Poolside's 118B-total / ~8B-active Mixture-of-Experts model for agentic coding and long-horizon software work. This repo keeps the same tokenizer, chat template, and Laguna custom code files, with the weights converted to MLX 6-bit group quantization.
This is a community conversion. Model architecture, license, intended use, and safety guidance belong to the original Poolside release.
Apple Silicon with enough unified memory for the weights plus KV/cache headroom
Why This Model Is Interesting
Sparse-MoE design: 256 routed experts plus one shared expert, with top-10 routing.
48-layer Laguna S architecture with a 1:3 full-attention to sliding-window layout.
512-token sliding window layers help keep long-context decode memory bounded.
Native reasoning controls through enable_thinking in the chat template.
Built for coding, tools, and long-horizon agent workflows rather than short chat only.
Base Model Benchmarks
These are Poolside's reported base-model results for Laguna S 2.1, included here for context. They are not fresh benchmark runs of this MLX quantization.
Benchmark
Laguna S 2.1
Terminal-Bench 2.1
70.2%
SWE-bench Multilingual
78.5%
SWE-Bench Pro
59.4%
DeepSWE
40.4%
SWE Atlas (Codebase QnA)
46.2%
Toolathlon Verified
49.7%
See the original model card for the full table, comparison models, methodology notes, and links to trajectories.
Install
Laguna support in MLX is still moving quickly. If your installed mlx-lm cannot import model_type: laguna, use a Laguna-capable branch until support lands in your preferred release.
The model config keeps MoE gate projections at 8-bit.
Tokenizer, chat template, and Laguna remote-code files are included from the source model.
Reasoning can be enabled, but many local clients behave better with enable_thinking=false unless they understand separate reasoning fields.
Known Caveats
This is a large local model. Leave memory headroom for prompts, KV cache, and the OS.
6-bit is a middle ground between the smaller 4-bit repo and the higher-fidelity 8-bit repo.
Some stable mlx-lm releases may not yet include Laguna support; a Laguna-capable branch may be required.
DFlash speculative decoding for Laguna is not wired through stock MLX-LM at the time of this upload. Use Poolside's vLLM/SGLang/TRT recipes for the official DFlash serving path.
The benchmark table above describes the base model, not a separate quantized eval run.
No measured memory tier is assigned here. The collections use published M3 Studio peaks with at least 25% nominal headroom; fit on other Macs is an estimate, and full context is not guaranteed. Start with short context and one request.
Runtime and evidence
The exact tested oMLX application version is not recorded here; a library version is not an app version. The original performance tables retain their benchmark conditions and speed figures; this documentation update adds no new test results.
Add the downloaded folder to oMLX model directories, refresh the list, and follow this card's architecture and MTP compatibility requirements before loading.
Try this in a new chat with a 128-token output limit:
Explain why the sky looks blue in three short sentences.
This is a demo prompt to try, not a recorded successful run; a captured demonstration for this documentation update is not yet available.
