Tess GGUF models

93 GGUF models in the Tess family, quantized by 20 uploaders. Sizes run from 610M to 118B parameters. The longest trained context is 1000K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
TE
Tess 4 27B
Tess · migtissera
Params27B
Context256K
Q4_K_M2.0 GB
ReasoningVision
TE
Tess-4.5-27B
Tess · migtissera
Params27B
Context256K
Q4_K_M2.0 GB
ReasoningVision
TE
Tess 4.5 27B
Tess · bartowski
Params27.3B
Context256K
Q4_K_M17.4 GB
ReasoningTool useVision
TE
Tess M Creative v1.0
Tess · TheBloke
Params34.4B
Context195K
Q4_K_M20.7 GB
GGUF
TE
migtissera_tess-m-v1.3
Tess · TheBloke
Params34.4B
Context195K
Q4_K_M20.7 GB
GGUF
TE
Tess 10.7B v1.5b
Tess · TheBloke
Params10.7B
Context4K
Q4_K_M6.5 GB
GGUF
TE
Tess 4 27B
Tess · bartowski
Params27.3B
Context256K
Q4_K_M17.8 GB
ReasoningTool useVision
TE
Tess 4 9B
Tess · bartowski
Params9.2B
Context256K
Q4_K_M6.0 GB
ReasoningTool useVision
TE
migtissera_tess-34b-v1.5b
Tess · TheBloke
Params34.4B
Context195K
Q4_K_M20.7 GB
GGUF
TE
migtissera_tess-xs-v1.1
Tess · TheBloke
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
TE
migtissera_tess-m-v1.1
Tess · TheBloke
Params34.4B
Context195K
Q4_K_M20.7 GB
GGUF
TE
Tess 4 9B
Tess · mradermacher
Params9.2B
Context256K
Q4_K_M5.8 GB
ReasoningTool useVision
TE
Tess 4.5 27B
Tess · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
ReasoningTool use
TE
Tess 4 27B ROCmFPX
Tess · lmcoleman
Params27.3B
Context256K
Smallest15.1 GB
ReasoningTool use
TE
Tess 7B v2.0
Tess · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
TE
migtissera_tess-xs-creative-v1.0
Tess · TheBloke
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
TE
Tess 4.5 27B
Tess · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
ReasoningTool useVision
TE
migtissera_tess-7b-v1.4
Tess · TheBloke
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
TE
Tess XS v1 3 yarn 128K i1
Tess · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
TE
Tess 34B v1.5b
Tess · mradermacher
Params34.4B
Context195K
Q4_K_M20.7 GB
GGUF
TE
Tess 3 7B SFT
Tess · mradermacher
Params7.25B
Context32K
Q4_K_M4.4 GB
GGUF
TE
Tess 4.1 35B A3B
Tess · mradermacher
Params35.5B
Context256K
Q4_K_M21.7 GB
ReasoningTool use
TE
Tess 34B v1.5b i1
Tess · mradermacher
Params34.4B
Context195K
Q4_K_M20.7 GB
GGUF
TE
Mn 12b Mm Tess Books
Tess · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
TE
Tess 7B v2.0
Tess · bartowski
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
TE
Tess 3 7B SFT
Tess · bartowski
Params7.25B
Context32K
Q4_K_M4.4 GB
GGUF
TE
Tess 4.1 35B A3B
Tess · mradermacher
Params35.5B
Context256K
Q4_K_M21.7 GB
ReasoningTool useVision
TE
Tess 10.7B V1.5B
Tess · mradermacher
Params10.7B
Context4K
Q4_K_M6.5 GB
GGUF
TE
Tess 3 7B SFT i1
Tess · mradermacher
Params7.25B
Context32K
Q4_K_M4.4 GB
GGUF
TE
Tess 4 9B
Tess · migtissera
Params9B
Context—
Q4_K_M0.0 GB
ReasoningTool use

About the Tess GGUF models

Tess is represented on ggufmodels.com by 93 GGUF models, quantized by 20 uploaders on Hugging Face. The most downloaded are Tess 4 27B, Tess-4.5-27B and Tess 4.5 27B. Parameter counts run from 610M to 118B, and the longest trained context window is 1000K tokens.

A Q4_K_M file of a Tess model is between 0.0 to 43.8 GB, which is the quant most people start with. Most files come from mradermacher (41), TheBloke (11) and RichardErkhov (8). The quants you will meet most often are Q4_K_M (78), Q2_K (76), Q3_K_S (72) and Q3_K_M (72), where the number is how many models offer that quant.

Frequently asked questions

Which Tess GGUF should I download?

The most downloaded Tess GGUF here is Tess 4 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 Tess model need?

Q4_K_M files of Tess models on this site range from 0.0 to 43.8 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 Tess GGUF files come from?

The most common quantizers here are mradermacher, TheBloke and RichardErkhov. 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