BO

Bonsai-8B

BonsaiGGUF by prism-mlUpdated 2026-04-18
Download on Hugging Face
Parameters8.2B
Context64K
Layers36
Architectureqwen3
Smallest quant1.2 GB
Quick answer

Bonsai-8B needs about 2.9 GB of memory at Q1_0 (a 1.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 1.2 GB (Q1_0) to 1.2 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

Bonsai-8B: 1‑bit Qwen3 model for efficient local inference

Bonsai-8B is an 8.2‑billion parameter Qwen3 model quantized to 1‑bit Q1_0 for llama.cpp. The GGUF file is 1.16 GB and requires about 2.9 GB of RAM at 8 k context. It is released under Apache‑2.0 and supports CUDA, Metal, Android, and CPU.

Good at

  • 1‑bit inference on modest GPUs
  • Fast generation with low memory footprint
  • Cross‑platform compatibility

Limits

  • No vision support
  • Requires 8 k context for memory estimate
  • No mixture‑of‑experts

Best for

  • Edge device inference
  • Rapid prototyping with low VRAM
  • Cost‑effective local LLM deployment

Who it’s for. Developers and researchers needing a lightweight language model that runs on consumer GPUs or CPUs. The model is ideal for applications where memory and speed are critical, such as local chatbots or embedded AI services.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q1_01.2 GB 2.9 GB
Fits Get file →
—1.2 GB 2.9 GB
Fits Get file →

For 8 GB VRAM, use Q1_0 (1.16 GB) which fits comfortably. If more memory is available, the same file size applies; no other quants are listed. The estimate of 2.9 GB RAM at 8 k context is approximate.

What GPU do you need for Bonsai-8B?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is Q1_0 (1.2 GB file, about 2.9 GB in use).

Which Bonsai-8B quant should you choose?

Q1_0 (1.2 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3
Parameters8.2B
Layers36
Trained context65,536 tokens
KV cache (fp16)144 KB per token

Source

Quantized byprism-ml
FamilyBonsai
Licenseapache-2.0
Downloads (HF)109,076
Last updated2026-04-18

Frequently asked questions about Bonsai-8B

How much VRAM does Bonsai-8B need?

About 2.9 GB at Q1_0 with an 8K context window. That is the 1.2 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Bonsai-8B on an 8 GB GPU?

Yes, with Q1_0: the 1.2 GB file needs about 2.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Bonsai-8B GGUF?

It depends on the quant: Q1_0 is 1.2 GB, file is 1.2 GB.

What context length does Bonsai-8B support?

The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.

Where can I download Bonsai-8B GGUF?

The files are on Hugging Face in the prism-ml/Bonsai-8B-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Bonsai-8B use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Bonsai-8B on 8 GB VRAM?

Yes, the 1‑bit Q1_0 GGUF file is 1.16 GB and requires about 2.9 GB of RAM at 8 k context, fitting on 8 GB VRAM.

Does Bonsai-8B support vision tasks?

No, the model has no vision capabilities.

Other GGUFs of Bonsai-8B-unpacked

Similar models

Browse all →

More from prism-ml

All by prism-ml →

More Bonsai models

All Bonsai →

Other small models

All small models →