Bonsai GGUF models

79 GGUF models in the Bonsai family, quantized by 55 uploaders. Sizes run from 6M to 27.3B parameters. The longest trained context is 256K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
BO
Bonsai-27B
Bonsai · lmstudio-community
Params27B
Context256K
Smallest3.8 GB
Vision
BO
Bonsai-8B
Bonsai · prism-ml
Params8.2B
Context64K
Smallest1.2 GB
GGUF
BO
Bonsai-1.7B
Bonsai · prism-ml
Params1.72B
Context32K
Smallest0.2 GB
GGUF
BO
Bonsai-4B
Bonsai · prism-ml
Params4B
Context32K
Smallest0.6 GB
GGUF
BO
Bonsai-27B
Bonsai · weareapexcreators
Params27B
Context256K
Smallest3.8 GB
Vision
BO
prism ml Bonsai 8B unpacked
Bonsai · bartowski
Params8.19B
Context64K
Q4_K_M5.2 GB
GGUF
BO
Bonsai 27b 1bit CRACK
Bonsai · dealignai
Params27B
Context256K
Smallest4.7 GB
ReasoningTool useVision
BO
Bonsai 2 27b VL Uncensored PTQ1 PTQ2 MTP
Bonsai · W-Zil
Params27B
Context256K
Smallest5.9 GB
Vision
BO
Bonsai-27B
Bonsai · vcruz305
Params26.9B
Context256K
Q4_K_M16.5 GB
ReasoningTool useVision
BO
Ternary Bonsai 2 27B CRACK MTP
Bonsai · ManniX-ITA
Params27.3B
Context256K
Smallest7.7 GB
ReasoningTool use
BO
bonsai image ternary 4B FLUX2 klein
Bonsai · biali
Params3.88B
Context—
Smallest1.4 GB
GGUF
BO
Thox1 27b
Bonsai · tommytracx
Params26.9B
Context256K
Smallest4.7 GB
ReasoningTool use
BO
Bonsai-27B
Bonsai · livadies
Params26.9B
Context256K
Smallest3.8 GB
ReasoningTool use
BO
Bonsai 27B antidoom 1bit DSpark
Bonsai · Danny-Dasilva
Params26.9B
Context4K
Smallest1.8 GB
ReasoningTool useVision
BO
bonsai 2b i1
Bonsai · mradermacher
Params2.61B
Context128K
Q4_K_M1.7 GB
GGUF
BO
bonsai 2b
Bonsai · mradermacher
Params2.61B
Context128K
Q4_K_M1.7 GB
GGUF
BO
bonsai image ternary 4B FLUX2 klein
Bonsai · Aatricks
Params3.88B
Context—
Smallest1.4 GB
GGUF
BO
TokForge Bonsai Image 4B
Bonsai · darkmaniac7
Params3.88B
Context40K
Q4_K_M2.5 GB
GGUF
BO
Bonsai-27B
Bonsai · leeaandrob
Params26.9B
Context256K
Smallest3.8 GB
ReasoningTool useVision
BO
Bonsai-27B
Bonsai · qelulab
Params26.9B
Context256K
Smallest3.8 GB
ReasoningTool use
BO
bonsai image binary 4B
Bonsai · Green-Sky
Params3.88B
Context—
Smallest0.8 GB
GGUF
BO
bonsai image ternary 4B
Bonsai · Green-Sky
Params3.88B
Context—
Smallest1.3 GB
GGUF
BO
Bonsai 8B requantized
Bonsai · lilyanatia
Params8.19B
Context64K
Smallest0.0 GB
GGUF
BO
Bonsai 27B GGUF Colab Prebuilt GPU
Bonsai · IamPradeep
Params26.9B
Context4K
Smallest1.8 GB
ReasoningTool useVision
BO
Bonsai 2 27B PQ2 0 MTP
Bonsai · groxaxo
Params27.3B
Context256K
Smallest7.6 GB
ReasoningTool use
BO
Bonsai-8B
Bonsai · IamPradeep
Params8.19B
Context64K
Smallest1.2 GB
ReasoningTool use
BO
Bonsai-8B
Bonsai · apothic
Params8.19B
Context64K
Smallest1.2 GB
ReasoningTool use
BO
bonsai2 dflash2 fastfork
Bonsai · zotowata
Params1.92B
Context256K
Smallest1.1 GB
ReasoningTool use
BO
Bonsai-27B
Bonsai · eugenehp
Params26.9B
Context256K
Smallest3.8 GB
ReasoningTool use
BO
Bonsai 8B Ternary RDNA4
Bonsai · Gorilla4X
Params8.19B
Context64K
Smallest2.2 GB
ReasoningTool use

About the Bonsai GGUF models

Bonsai is represented on ggufmodels.com by 79 GGUF models, quantized by 55 uploaders on Hugging Face. The most downloaded are Bonsai-27B, Bonsai-8B and Bonsai-1.7B. Parameter counts run from 6M to 27.3B, and the longest trained context window is 256K tokens.

A Q4_K_M file of a Bonsai model is between 1.1 to 16.5 GB, which is the quant most people start with. Most files come from mradermacher (8), Hagwell (4) and sinatras (3). The quants you will meet most often are Q1_0 (39), Q2_K (13), Q4_K_M (10) and Q8_0 (8), where the number is how many models offer that quant.

Frequently asked questions

Which Bonsai GGUF should I download?

The most downloaded Bonsai GGUF here is Bonsai-27B. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.

How much VRAM does a Bonsai model need?

Q4_K_M files of Bonsai models on this site range from 1.1 to 16.5 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.

Where do Bonsai GGUF files come from?

The most common quantizers here are mradermacher, Hagwell and sinatras. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.

Keep browsing