Bonsai 8B MLX 2.25bit by inferencerlabs

 »  All LLMs  »  inferencerlabs  »  Bonsai 8B MLX 2.25bit   URL Share it on

Bonsai 8B MLX 2.25bit is an open-source language model by inferencerlabs. Features: 8b LLM, VRAM: 2.3GB, Context: 64K, Quantized, LLM Explorer Score: 0.3.

  1bit   2-bit Base model:prism-ml/bonsai-8b-... Base model:quantized:prism-ml/...   Conversational   En   Mlx   Quantized   Qwen3   Region:us   Safetensors

Bonsai 8B MLX 2.25bit Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Bonsai 8B MLX 2.25bit Parameters and Internals

LLM NameBonsai 8B MLX 2.25bit
Repository 🤗https://huggingface.co/inferencerlabs/Bonsai-8B-MLX-2.25bit 
Base Model(s)  Bonsai 8B Mlx 1bit   prism-ml/Bonsai-8B-mlx-1bit
Model Size8b
Required VRAM2.3 GB
Updated2026-04-29
Maintainerinferencerlabs
Model Typeqwen3
Model Files  2.3 GB
Supported Languagesen
Quantization Type1bit
Model ArchitectureQwen3ForCausalLM
Context Length65536
Model Max Length65536
Transformers Version4.57.6
Padding Token<|endoftext|>
Vocabulary Size151669
Errorsreplace

Best Alternatives to Bonsai 8B MLX 2.25bit

Best Alternatives
Context / RAM
Downloads
Likes
BehChat SFTv2 Mixed Ckpt 6128K / 16.4 GB1310
BehChat SFTv3 Ckpt1128K / 16.4 GB420
...0528 Qwen3 8B Unsloth Bnb 4bit128K / 7.5 GB312112
DeepSeek R1 0528 Qwen3 8B 4bit128K / 4.6 GB23575
...Seek R1 0528 Qwen3 8B Bnb 4bit128K / 6.1 GB48310
Qwen3 8B LQA 14e Full128K / 16.4 GB50
...Seek R1 0528 Qwen3 8B 4bit DWQ128K / 4.6 GB1748
...0528 Qwen3 8B Unsloth Bnb 4bit128K / 16.4 GB50
Annie Lite V0.2.9 Qwen3 8B80K / 16.4 GB90
Bonsai 8B Mlx 1bit64K / 1.3 GB55259198
Note: green Score (e.g. "73.2") means that the model is better than inferencerlabs/Bonsai-8B-MLX-2.25bit.

Rank the Bonsai 8B MLX 2.25bit Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 53834 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a