GGUF models by zelk12

79 GGUF models quantized by zelk12 on Hugging Face. Sizes run from 2.9B to 11.8B parameters. The longest trained context is 128K tokens.

Most downloadedNewestLargestLongest contextSmallest
GE
MT gemma 4 8B E4B
Gemma · zelk12
Params7.52B
Context128K
Smallest6.2 GB
ReasoningTool useVision
GE
MT4 Gen2_gemma 3 12B
Gemma · zelk12
Params11.8B
Context128K
Smallest9.7 GB
Vision
GE
MT Gen1 gemma 2 9B Q6 K
Gemma · zelk12
Params9.24B
Context8K
Smallest7.6 GB
GGUF
GE
MT3 Gemma 3 12B
Gemma · zelk12
Params11.8B
Context128K
Smallest9.7 GB
Vision
GE
MT Gen9 gemma 2 9B Q6 K
Gemma · zelk12
Params9.24B
Context8K
Smallest7.6 GB
GGUF
GE
MT5 gemma 2 9B Q6 K
Gemma · zelk12
Params9.24B
Context8K
Smallest7.6 GB
GGUF
GE
MT Gen13 Gemma 2 9B
Gemma · zelk12
Params9.24B
Context8K
Smallest7.6 GB
GGUF
GE
MT2 Gen5 gemma 2 9B Q6 K
Gemma · zelk12
Params9.24B
Context8K
Smallest7.6 GB
GGUF
GE
MT1 Gen9 gemma 2 9B Q6 K
Gemma · zelk12
Params9.24B
Context8K
Smallest7.6 GB
GGUF
GE
gemma 2 S2MTM 9B Q6 K
Gemma · zelk12
Params9.24B
Context8K
Smallest7.6 GB
GGUF
GE
MT4 gemma 2 9B Q6 K
Gemma · zelk12
Params9.24B
Context8K
Smallest7.6 GB
GGUF
GE
MT3 Gen2_gemma 3 12B
Gemma · zelk12
Params11.8B
Context128K
Smallest9.7 GB
Vision
GE
MT4 Gen3 gemma 2 9B Q6 K
Gemma · zelk12
Params9.24B
Context8K
Smallest7.6 GB
GGUF
GE
MT3 Gen11 gemma 2 9B Q6 K
Gemma · zelk12
Params9.24B
Context8K
Smallest7.6 GB
GGUF
GE
MT5 Gen1 gemma 2 9B Q6 K
Gemma · zelk12
Params9.24B
Context8K
Smallest7.6 GB
GGUF
GE
R1 Gemma 3 4B Multimodal Test
Gemma · zelk12
Params3.88B
Context128K
Smallest3.2 GB
Reasoning
GE
MT3 Gen4 gemma 2 9B Q6 K
Gemma · zelk12
Params9.24B
Context8K
Smallest7.6 GB
GGUF
GE
MT4 Gen1 gemma 2 9B Q6 K
Gemma · zelk12
Params9.24B
Context8K
Smallest7.6 GB
GGUF
GE
MT4 Gemma 3 12B
Gemma · zelk12
Params11.8B
Context128K
Smallest9.7 GB
Vision
GE
MTMMe Merge gemma 2 9B Q6 K
Gemma · zelk12
Params9.24B
Context8K
Smallest7.6 GB
GGUF
GE
recoilme gemma 2 Gutenberg Doppel 9B v0.1 Q6 K
Gemma · zelk12
Params9.24B
Context8K
Smallest7.6 GB
GGUF
GE
MT2 Gemma 3 12B
Gemma · zelk12
Params11.8B
Context128K
Smallest9.7 GB
Vision
GE
Gemma2 9B It Psy10K
Gemma · zelk12
Params9.24B
Context8K
Smallest7.6 GB
GGUF
GE
recoilme gemma 2 Ataraxy 9B v0.2 Q6 K
Gemma · zelk12
Params9.24B
Context8K
Smallest7.6 GB
GGUF
IN
Internlm2_5 7b Chat
InternLM · zelk12
Params7.74B
Context32K
Smallest6.4 GB
GGUF
GE
MT3 Max Merge 02012025163610 gemma 2 9B Q6 K
Gemma · zelk12
Params9.24B
Context8K
Smallest7.6 GB
GGUF
GE
Test01012025155054 gemma 2 Q6 K
Gemma · zelk12
Params2.9B
Context8K
Smallest2.4 GB
GGUF
GE
MT gemma 2 9B Q6 K
Gemma · zelk12
Params9.24B
Context8K
Smallest7.6 GB
GGUF
GE
MT2 gemma 2 9B Q6 K
Gemma · zelk12
Params9.24B
Context8K
Smallest7.6 GB
GGUF
GE
MT2 Gen2_gemma 3 12B
Gemma · zelk12
Params11.8B
Context128K
Smallest9.7 GB
Vision

About zelk12 on Hugging Face

zelk12 has published 79 GGUF models that ggufmodels.com tracks, across families such as Gemma and InternLM. The most downloaded are MT gemma 4 8B E4B, MT4 Gen2_gemma 3 12B and MT Gen1 gemma 2 9B Q6 K.

The quants zelk12 publishes most often are Q6_K (79). Parameter counts run from 2.9B to 11.8B, and the longest trained context window is 128K tokens.

Frequently asked questions

What GGUF models has zelk12 published?

79 models are listed here, mainly from the Gemma and InternLM families. The most downloaded is MT gemma 4 8B E4B.

Which quants does zelk12 publish?

The most common are Q6_K (79 models).

Keep browsing