Mellum GGUF models

91 GGUF models in the Mellum family, quantized by 35 uploaders. Sizes run from 833M to 12.6B parameters. The longest trained context is 128K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
ME
Mellum 4b sft kotlin
Mellum · smithbon22021106
Params4.02B
Context8K
Smallest4.3 GB
Coding
ME
Mellum 4b Sft All
Mellum · LLukas22
Params4.02B
Context8K
Q4_K_M2.6 GB
Coding
ME
Mellum2 BF16
Mellum · shailesh83
Params12.1B
Context128K
Smallest24.3 GB
ReasoningTool use
ME
Mellum2 Thinking
Mellum · shailesh83
Params12.1B
Context128K
Q4_K_M8.1 GB
ReasoningTool use

Keep browsing