Get the latest setups
Models/Bonsai/Bonsai 27B · original ternary
Text / prism-ml

Bonsai 27B · original ternary

The original Bonsai 27B generation, based on Qwen3.6-27B. This is its ternary GGUF package; Bonsai 2 is a newer Qwen3.8-based model.

EstimatedRepository opened Jul 4, 2026Source checked 9/23/2026Version: 86e89f34
LOCALRENTED GPUOPEN WEIGHTS
Freshness 67 out of 100. Repository age: 103 days old, Jul 4, 2026. Measures age, not quality.
Popularity 79 out of 100. 586,187 downloads in 30 days; 1,424 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
6.7 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 generationBonsai 27B · original ternaryOriginal · ternary packageBonsai 27B · original 1-bitOriginal · 1-bit package

Best for

  • Local text generation with llama.cpp on CUDA, Metal, or CPU
  • On-device reasoning and conversational tasks
  • Agentic tool-use scenarios
  • Math and coding assistance
  • Speculative decoding with the included DSpark drafter layer

Tradeoffs

  • Only text-generation pipeline is specified; multimodal capabilities are not stated beyond the vision tower.
  • Requires custom llama.cpp forks or kernels for CUDA and Metal; standard support is not guaranteed.
  • Deployment footprint and speed may vary; reported performance is based on specific hardware and paths.
  • License is apache-2.0 as listed, but no additional warranty or compatibility details are provided.
  • No independent testing or verification is claimed.

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 Ternary-Bonsai-27B-PQ2_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.
Popularity 90 out of 100. 4,849,199 downloads in 30 days; 2,697 lifetime likes. Checked Oct 15, 2026. Measures adoption, 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.
Popularity 84 out of 100. 1,238,583 downloads in 30 days; 4,519 lifetime likes. Checked Oct 15, 2026. Measures adoption, 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 →