GGUF models by kolosal

41 GGUF models quantized by kolosal on Hugging Face. Sizes run from 494M to 32.8B parameters. The longest trained context is 128K tokens.

Most downloadedNewestLargestLongest contextSmallest
DE
Deepseek R1 Llama 8B
DeepSeek · kolosal
Params8.03B
Context128K
Q4_K_M4.9 GB
ReasoningTool use
LL
Llama 3.2 1B Instruct
Llama · kolosal
Params1.24B
Context128K
Q4_K_M0.8 GB
Tool use
GE
gemma-2-9b-it
Gemma · kolosal
Params9.24B
Context8K
Smallest6.0 GB
GGUF
QW
Qwen3 Embedding 8B Bf16
Qwen · kolosal
Params7.57B
Context40K
Q4_K_M4.7 GB
EmbeddingTool use
PH
Phi 4 Mini Instruct
Phi · kolosal
Params3.84B
Context128K
Q4_K_M2.5 GB
Tool use
DE
Deepseek R1 Qwen 7B
DeepSeek · kolosal
Params7.62B
Context128K
Q4_K_M4.7 GB
ReasoningTool use
GE
Google_Gemma 3 1b It
Gemma · kolosal
Params1B
Context32K
Q4_K_M0.8 GB
GGUF
GE
Google_Gemma 3 27b It
Gemma · kolosal
Params27B
Context128K
Q4_K_M16.5 GB
GGUF
QW
Qwen3-14B
Qwen · kolosal
Params14.8B
Context40K
Smallest9.2 GB
ReasoningTool use
QW
Qwen3 Embedding 0.6B Bf16
Qwen · kolosal
Params596M
Context32K
Smallest0.6 GB
EmbeddingReasoningTool use
QW
Qwen3-32B-128K
Qwen · kolosal
Params32.8B
Context128K
Smallest20.0 GB
ReasoningTool use

Keep browsing