LocalClaw/LLM/Bonsai 27B
Open-weight local LLM

Bonsai 27B

Catalogue summary: PrismML low-bit model derived from Qwen 3.6 27B. Official Apache 2.0 ternary (7.2GB deployed) and 1-bit (3.9GB) builds retain multimodal, reasoning and agentic capabilities through custom GGUF and MLX runtimes.

Repository editorial metadata; verify comparative claims in the linked upstream material.

16 GB catalogue minimum16 GB RAMTernary Q2_0_g128Coding assistant
Choose an app

This model needs a special runtime. Unsupported apps are clearly marked.

Compare models
LM StudioNot available for this model
UnslothNot available for this model
OllamaNot available for this model
Open on Hugging FaceFiles, licence and available downloads
llama.cppNot available for this model
Use with LocalClawOptional workspace after the model is installed
This model needs its official runtimePrismML llama.cpp / MLX
Parameters
27.3B (ternary / 1-bit)
Minimum RAM
16 GB
Model size
7.2 GB
Quantization
Ternary Q2_0_g128

Can Bonsai 27B run locally?

Bonsai 27B has a catalogue minimum of 16 GB RAM with Ternary Q2_0_g128. Actual memory use and speed vary by context length, runtime, backend and system headroom.

Use the official PrismML llama.cpp / MLX setup. The current low-bit files are not a stock LM Studio install.

Model sourcePublic GGUF repository (verified 2026-09-07): prism-ml/Ternary-Bonsai-27B-ggufUpstream releasePaper or model cardLicence text
chatcodereasoningvisionagenticmultimodaledgespeed

Install path

01
Check RAM fitMinimum 16 GB RAM. Start with the Ternary Q2_0_g128 quant.
02
Load the modelFollow the official PrismML llama.cpp / MLX instructions. Stock LM Studio support is not confirmed.
03
Control locallyUse LocalClaw to manage models, agents, chat, channels and scheduled OpenClaw work.

Catalogue record

  • Family: bonsai
  • Parameters: 27.3B (ternary / 1-bit)
  • Recommended quantization: Ternary Q2_0_g128
  • Catalogue minimum RAM: 16 GB
  • Catalogue model size: 7.2 GB
  • Tags: chat, code, reasoning, vision, agentic, multimodal, edge, speed, long-context

Practical limits

  • Catalogue RAM is a minimum estimate, not a guarantee for every context length or runtime.
  • Speed and memory use vary by quantization, backend, context length and system headroom.
  • Verify architecture, licence and usage restrictions in the linked upstream material before deployment.

Catalogue tags

  • chat
  • code
  • reasoning
  • vision
  • agentic
  • multimodal

Capability profile

Repository catalogue ratings used by LocalClaw's editorial rubric. They are not a standardized third-party benchmark.

speed
9
quality
8
coding
9
reasoning
9

Technical notes

Developer
PrismML
License
Apache 2.0
Context window
262,144 tokens
Architecture
Qwen 3.6 27B-derived hybrid-attention multimodal transformer compressed into native ternary Q2_0_g128 and binary Q1_0_g128 weights.

This model fits these next steps

Hardware fit is based on LocalClaw's RAM tier, model size and quantization metadata. Always leave memory headroom for your OS and runtime.

Starter desktopMac mini M4 16GBPortable fitMacBook Air M4 16GBBest 16GB models16GB RAM guide

Related catalogue entries

Linked mechanically by family, shared tags and nearby RAM tier; this is not a quality ranking.

Agents-A1 4B 4BLing-3.0-tiny 7.9B (1.3B active, MoE)Muse Glimmer 30B 29.8B multimodalQwen 3.6 35B-A3B 35B (3B active, MoE)Qwen3.8-27B 27BGemma 4 12B 12BOrnith-1.5-9B 9BLFM2.5-2.6B 2.7B

Where to go next