Ternary GGUF models

119 GGUF models in the Ternary family, quantized by 73 uploaders. Sizes run from 2M to 28.9B parameters. The longest trained context is 256K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
TE
Ternary Bonsai 8B
Ternary · prism-ml
Params8.19B
Context64K
Smallest2.2 GB
GGUF
TE
Ternary Bonsai 2 27B Uncensored Heretic
Ternary · OS-Software
Params27B
Context256K
Smallest5.9 GB
Vision
TE
Ternary Bonsai 2 27B Uncensored Heretic v2
Ternary · OS-Software
Params27B
Context256K
Smallest5.9 GB
Vision
TE
Ternary Bonsai 2 27B Abliterated v2 PQ2 0 MTP
Ternary · BoldingBuilds
Params26.9B
Context256K
Smallest7.2 GB
ReasoningTool use
TE
Ternary Bonsai 2 27B Abliterated PTQ1 0
Ternary · BoldingBuilds
Params26.9B
Context256K
Smallest5.9 GB
ReasoningTool use
TE
Ternary Bonsai 2 27B Abliterated
Ternary · Hikari07jp
Params27B
Context256K
Smallest7.2 GB
GGUF
TE
Swift Bonsai 2
Ternary · ukisai
Params27B
Context256K
Smallest5.9 GB
Reasoning
TE
Offrail 27B Uncensored
Ternary · sudoingx
Params28.6B
Context256K
Smallest6.3 GB
GGUF
TE
Ternary Bonsai 2 27B 262k
Ternary · CaryPalmer
Params27.3B
Context256K
Smallest6.4 GB
Tool use
TE
Ternary Bonsai 2 27B Abliterated PQ2 0 MTP
Ternary · BoldingBuilds
Params27B
Context256K
Smallest7.2 GB
GGUF
TE
Ternary Bonsai 2 27B Heretic Satellite
Ternary · HybridRMD
Params27B
Context256K
Q4_K_M16.5 GB
GGUF
TE
Ternary Bonsai 1.7B
Ternary · prism-ml
Params1.72B
Context32K
Smallest0.5 GB
GGUF
TE
Bonsai-27B
Ternary · Hikari07jp
Params27B
Context256K
Smallest7.2 GB
GGUF
TE
Ternary Bonsai 4B
Ternary · prism-ml
Params4B
Context32K
Smallest1.1 GB
GGUF
TE
Ternary Bonsai 2 27B DFlash2
Ternary · ProCreations
Params1.92B
Context256K
Smallest2.1 GB
GGUF
TE
Ternary-Bonsai-2-27B-Uncensored
Ternary · gaston-parravicini
Params27B
Context256K
Smallest7.1 GB
Reasoning
TE
Ternary Bonsai 2 27B MTP
Ternary · ManniX-ITA
Params27.3B
Context256K
Smallest6.4 GB
GGUF
TE
Ingot XVI 27B Q2
Ternary · dendriteholdings
Params26.9B
Context256K
Smallest5.9 GB
ReasoningTool use
TE
Ternary Bonsai 2 27B Abliterated swift cap PQ2 0 MTP
Ternary · hotdogs
Params27.3B
Context256K
Smallest7.6 GB
ReasoningVision
TE
Ternary Bonsai 2 27B Abliterated PTQ1 0 MTP Q4 0
Ternary · Cheurteen
Params26.9B
Context256K
Smallest5.9 GB
ReasoningTool use
TE
Bonsai 27b Ternary CRACK
Ternary · dealignai
Params27B
Context256K
Smallest8.2 GB
ReasoningTool useVision
TE
Ternary Bonsai 2 27B abliterated
Ternary · Override-6
Params27B
Context256K
Smallest5.9 GB
GGUF
TE
Bonsai JEV
Ternary · dakebakery
Params26.9B
Context—
Smallest0.2 GB
GGUF
TE
jev Ternary Bonsai 2 27B Abliterated PTQ1 0
Ternary · hotdogs
Params27B
Context256K
Smallest5.9 GB
Vision
TE
Ternary Bonsai 2 27B ABLITERATED UNCENSORED PHILADELPHIA CLASS
Ternary · PhillyLabs
Params26.9B
Context—
Smallest0.0 GB
GGUF
TE
bonsai 2 27b mtp
Ternary · decent-jawfish
Params27.3B
Context256K
Smallest7.6 GB
GGUF
TE
Ternary Bonsai 4b Abliterated v2
Ternary · Rootkit7
Params4B
Context32K
Q4_K_M2.5 GB
GGUF
TE
TokForge Bonsai 2 27B
Ternary · darkmaniac7
Params27B
Context256K
Smallest5.9 GB
GGUF
TE
Sakura Micro Bonsai 2 GSQ RCO
Ternary · webmp3
Params27B
Context256K
Smallest5.7 GB
GGUF
TE
Ternary Bonsai 2 27B Abliterated v2 PQ2 0 MTP
Ternary · timfromhcs
Params27B
Context256K
Smallest7.2 GB
Reasoning

About the Ternary GGUF models

Ternary is represented on ggufmodels.com by 119 GGUF models, quantized by 73 uploaders on Hugging Face. The most downloaded are Ternary Bonsai 8B, Ternary Bonsai 2 27B Uncensored Heretic and Ternary Bonsai 2 27B Uncensored Heretic v2. Parameter counts run from 2M to 28.9B, and the longest trained context window is 256K tokens.

A Q4_K_M file of a Ternary model is between 1.1 to 16.5 GB, which is the quant most people start with. Most files come from jinreiyu (6), ChezRD (4) and BoldingBuilds (4). The quants you will meet most often are Q2_0 (26), F16 (20), Q4_K_M (15) and Q2_K (12), where the number is how many models offer that quant.

Frequently asked questions

Which Ternary GGUF should I download?

The most downloaded Ternary GGUF here is Ternary Bonsai 8B. 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 Ternary model need?

Q4_K_M files of Ternary 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 Ternary GGUF files come from?

The most common quantizers here are jinreiyu, ChezRD and BoldingBuilds. 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