GGUF models by FreedomAISVR

89 GGUF models quantized by FreedomAISVR on Hugging Face. Sizes run from 334M to 70.6B parameters. The longest trained context is 1024K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
Qwen Image Edit Rapid AIO NSFW v23 NVFP4
Qwen · FreedomAISVR
Params20.4B
Context32K
Smallest4.1 GB
GGUF
QW
Qwen3.6 35B A3B
Qwen · FreedomAISVR
Params34.7B
Context256K
Smallest19.8 GB
Vision
GE
Gemma 4 12B it QAT NVFP4
Gemma · FreedomAISVR
Params11.9B
Context256K
Smallest7.2 GB
Vision
GE
Gemma 4 12B it QAT MXFP4
Gemma · FreedomAISVR
Params11.9B
Context256K
Smallest6.9 GB
ReasoningTool useVision
GE
Gemma 4 E4B it NVFP4
Gemma · FreedomAISVR
Params7.52B
Context128K
Smallest5.2 GB
ReasoningTool useVision
GE
Gemma 4 26B A4B it QAT NVFP4
Gemma · FreedomAISVR
Params25.2B
Context256K
Smallest14.4 GB
ReasoningTool useVision
QW
Qwen3.5 4B
Qwen · FreedomAISVR
Params4.21B
Context256K
Smallest2.5 GB
ReasoningTool useVision
QW
Qwen3.5 9B
Qwen · FreedomAISVR
Params8.95B
Context256K
Smallest5.3 GB
Vision
QW
Qwen3.6 35B A3B NVFP4
Qwen · FreedomAISVR
Params34.7B
Context256K
Smallest19.7 GB
ReasoningTool useVision
QW
Qwen3.8 27b
Qwen · FreedomAISVR
Params27.3B
Context256K
Smallest14.9 GB
ReasoningTool useVision
QW
Qwen3.6 35B A3B Claude 4.7 Distill MXFP4 MOE
Qwen · FreedomAISVR
Params35.5B
Context256K
Smallest20.3 GB
ReasoningTool use
GE
Gemma 4 12b It
Gemma · FreedomAISVR
Params11.9B
Context256K
Smallest7.0 GB
ReasoningTool useVision
GE
Gemma 4 12b It
Gemma · FreedomAISVR
Params11.9B
Context256K
Smallest6.6 GB
ReasoningTool useVision
GE
Gemma 4 E4B it Ultra Uncensored Heretic NVFP4
Gemma · FreedomAISVR
Params7.52B
Context128K
Smallest5.2 GB
ReasoningTool useVision
GP
gpt oss 20B NVFP4
gpt-oss · FreedomAISVR
Params20.9B
Context128K
Smallest12.7 GB
Tool use
QW
Mimo v2.6 Distill Qwen 9b
Qwen · FreedomAISVR
Params8.95B
Context256K
Smallest5.3 GB
ReasoningTool useVision
GE
Gemma 4 26B A4B it NVFP4
Gemma · FreedomAISVR
Params25.2B
Context256K
Smallest14.4 GB
ReasoningVision
GE
Gemma 4 12B it Uncensored Heretic NVFP4
Gemma · FreedomAISVR
Params11.9B
Context256K
Smallest7.0 GB
ReasoningTool useVision
QW
Qwen3.5 9B MTP NVFP4
Qwen · FreedomAISVR
Params456M
Context256K
Smallest5.5 GB
Vision
QW
Qwen3 Coder 30B A3B MXFP4 MOE
Qwen · FreedomAISVR
Params30.5B
Context256K
Smallest17.1 GB
CodingTool use
GP
GPT-OSS-20B
gpt-oss · FreedomAISVR
Params20.9B
Context128K
Smallest12.1 GB
Tool use
GE
Gemma 4 26B A4B it MXFP4 MOE
Gemma · FreedomAISVR
Params25.2B
Context256K
Smallest14.7 GB
ReasoningVision
QW
Qwen36 35b A3B
Qwen · FreedomAISVR
Params35.5B
Context256K
Smallest20.3 GB
ReasoningTool useVision
QW
Qwen36 35b A3B
Qwen · FreedomAISVR
Params35.5B
Context256K
Smallest20.2 GB
ReasoningTool useVision
DI
DiffusionGemma 26B A4B it NVFP4
Diffusiongemma · FreedomAISVR
Params25.2B
Context256K
Smallest14.4 GB
ReasoningTool useVision
GE
Gemma 4 26B A4B it QAT MXFP4
Gemma · FreedomAISVR
Params25.2B
Context256K
Smallest14.7 GB
ReasoningTool useVision
GE
Gemma 4 31B It
Gemma · FreedomAISVR
Params30.7B
Context256K
Smallest17.7 GB
ReasoningTool useVision
QW
Qwen3.5 9B Instruct MTP MXFP4
Qwen · FreedomAISVR
Params456M
Context256K
Smallest5.4 GB
Vision
QW
Qwen3.5 9B Instruct MXFP4
Qwen · FreedomAISVR
Params8.95B
Context256K
Smallest5.3 GB
ReasoningTool useVision
QW
Qwen3.6 35b A3B
Qwen · FreedomAISVR
Params34.7B
Context256K
Smallest19.7 GB
ReasoningTool use

About FreedomAISVR on Hugging Face

FreedomAISVR has published 89 GGUF models that ggufmodels.com tracks, across families such as Qwen, Gemma and Mistral. The most downloaded are Qwen Image Edit Rapid AIO NSFW v23 NVFP4, Qwen3.6 35B A3B and Gemma 4 12B it QAT NVFP4.

The quants FreedomAISVR publishes most often are MXFP4 (30) and MXFP4_MOE (13). Parameter counts run from 334M to 70.6B, and the longest trained context window is 1024K tokens.

Frequently asked questions

What GGUF models has FreedomAISVR published?

89 models are listed here, mainly from the Qwen, Gemma and Mistral families. The most downloaded is Qwen Image Edit Rapid AIO NSFW v23 NVFP4.

Which quants does FreedomAISVR publish?

The most common are MXFP4 (30 models) and MXFP4_MOE (13 models).

Keep browsing