Models/Bonsai/Bonsai 27B · original 1-bit

Text / prism-ml

Bonsai 27B · original 1-bit

The original Qwen3.6-based Bonsai 27B in its smaller 1-bit GGUF package. Bonsai 2 is a separate, newer generation.

EstimatedRepository opened Jul 4, 2026Source checked 9/23/2026Version: f10afb35

LOCALRENTED GPUOPEN WEIGHTS

Freshness 67 out of 100. Repository age: 103 days old, Jul 4, 2026. Measures age, not quality.

Popularity 76 out of 100. 403,985 downloads in 30 days; 920 lifetime likes. Checked Oct 15, 2026. Measures adoption, not quality.

What do these scores mean?

Two ways to compare models. Neither score measures answer quality, benchmark performance, or whether a model fits your machine.

Freshness · release age

A new release starts at 100. The score halves every 180 days: 100 × 2^(−age in days / 180). When the release date is unavailable, a repository date is a fallback—not proof of when the model was released. Missing dates stay unscored.

Check the date source

Popularity · adoption

Downloads over the past 30 days carry 80% of the score; lifetime likes carry 20%. Both use a logarithmic scale, capped at 10 million downloads and 100,000 likes. If likes are unavailable, downloads carry all the weight. Missing download statistics stay unscored.

round(80 × min(1, log10(1 + downloads) / 7) + 20 × min(1, log10(1 + likes) / 5))

Check the statistics source

Scores as of Oct 15, 2026. Statistics checked Oct 15, 2026. Statistics are marked for refresh after 72 hours.Full scoring method

At a glance

Architecture: unknown
License: apache-2.0
Disk space: 3.5 GB
Software: PrismML llama.cpp fork

View the model source

MY HARDWARE

Will it run on your machine?

Save your machine to see a personalized rating and its reasoning.

Add my hardware

Which Bonsai is this?

Bonsai 2 is the newer Qwen3.8-based release. The original Bonsai 27B is Qwen3.6-based and has separate ternary and smaller 1-bit packages. A different fit badge can also reflect different evidence: Bonsai 2 has a publisher RTX 5090 measurement; the original packages have a memory-based estimate for that card.

Bonsai 2 · 27BNew generation Bonsai 27B · original ternaryOriginal · ternary package Bonsai 27B · original 1-bitOriginal · 1-bit package

Best for

Text generation via llama.cpp using GGUF Q1_0_g128 weights
Conversational or agentic tasks on local hardware where the model card describes support
On-device inference with CUDA, Metal, or CPU backends as listed in the model card
Long-context work up to the stated 262K-token window with the described 4-bit KV cache
Speculative decoding on a CUDA serving path using the provided DSpark drafter

Tradeoffs

Facts not stated in the source data, including specific compatibility beyond the listed backends, are not inferred
The model card does not state performance guarantees; any benchmark or speed figures are source claims and are not independently verified here
Hardware requirements are not fully specified; the source only mentions CUDA, Metal, CPU, and some example devices
Quantized 1-bit weights and the custom kernels may require the linked llama.cpp fork; support outside that setup is not established in the source
No purchase recommendation, testing claim, or license interpretation beyond the provided apache-2.0 metadata is made

Ways to run it

PrismML llama.cpp fork · Windows, macOS, Linux

Repository-specific command in publisher documentation; confirm dependencies and hardware in the source.

./build/bin/llama-cli  -m Bonsai-27B-Q1_0.gguf  -p "Explain quantum computing in simple terms."  -n 256  --temp 0.7 --top-p 0.95 --top-k 20  -ngl 99

Official instructions

Explore its uses

GGUFTEXT-GENERATION

Keep exploring

Text

Prism ML

Bonsai 2 · 27B

A compressed 27B-class reasoning model with publisher-provided GGUF packs and a dedicated llama.cpp fork for CUDA, Metal, and CPU.

Freshness 90 out of 100. Release age: 28 days old, Sep 17, 2026. Measures age, not quality.

MODEL SIZE27.36B

LOCALRENTED GPU

Released Sep 17, 2026

Text

DeepSeek

DeepSeek V4.1 Flash

A multimodal reasoning model with a compressed key-value cache, published as open weights.

Freshness 87 out of 100. Repository age: 35 days old, Sep 10, 2026. Measures age, not quality.

Arena Open Source Text: rank 5 of 225. Ranked model: deepseek-v4.1-flash-max. Export dated Oct 13, 2026. Source checked Oct 15, 2026. Human preference ranking, not hardware suitability.+3

LOCALRENTED GPU

Repository opened Sep 10, 2026

Text

Qwen

Qwen3.8

Explore 4 versions of Qwen3.8. Compare model sizes, packages, hardware requirements, and available setups.

4 versionsCompare sizes & formats

LOCALRENTED GPU

Compare versions →