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
Mellum2.1-12B-A2.5B-Thinking
Mellum · JetBrains
Params12.1B
Context128K
Q4_K_M8.1 GB
Reasoning
ME
Mellum2 12B A2.5B Instruct
Mellum · JetBrains
Params12.1B
Context128K
Smallest12.9 GB
GGUF
ME
Mellum2 12B A2.5B Instruct
Mellum · JetBrains
Params12.1B
Context128K
Q4_K_M8.1 GB
GGUF
ME
Mellum2.1 12B A2.5B Thinking
Mellum · bartowski
Params12.1B
Context128K
Q4_K_M8.8 GB
Reasoning
ME
Mellum2 12B A2.5B Instruct
Mellum · bartowski
Params12.1B
Context128K
Q4_K_M8.2 GB
GGUF
ME
Abliterated
Mellum · alexwkleung
Params12.1B
Context128K
Q4_K_M8.1 GB
CodingReasoning
ME
Mellum2.1-12B-A2.5B-Thinking
Mellum · wepiqx
Params12.1B
Context128K
Smallest7.0 GB
CodingReasoning
ME
Mellum2 12B A2.5B Thinking
Mellum · bartowski
Params12.1B
Context128K
Q4_K_M8.2 GB
Reasoning
ME
Mellum2.1 12B A2.5B Thinking MTP
Mellum · bartowski
Params12.6B
Context128K
Q4_K_M9.0 GB
ReasoningTool use
ME
Mellum2 12B A2.5B Thinking
Mellum · JetBrains
Params12.1B
Context128K
Q4_K_M8.1 GB
Reasoning
ME
Mellum2.1 12B A2.5B Thinking Abliterated
Mellum · mradermacher
Params12.1B
Context128K
Q4_K_M8.1 GB
ReasoningTool use
ME
Mellum2 12B A2.5B Instruct
Mellum · mradermacher
Params12.1B
Context128K
Q4_K_M8.1 GB
Tool use
ME
Mellum2.1 12B A2.5B Thinking
Mellum · prithivMLmods
Params12.1B
Context128K
Q4_K_M8.1 GB
ReasoningTool use
ME
Mellum2.1 12B A2.5B Thinking Abliterated
Mellum · mradermacher
Params12.1B
Context128K
Q4_K_M8.1 GB
ReasoningTool use
ME
Mellum2 12B A2.5B Thinking Abliterated
Mellum · mradermacher
Params12.1B
Context128K
Q4_K_M8.1 GB
ReasoningTool use
ME
Mellum2 12B A2.5B Claude 4.6 4.8 Opus Thinking
Mellum · yuxinlu1
Params12.1B
Context128K
Q4_K_M8.1 GB
CodingReasoning
ME
Mellum2 12B A2.5B Instruct SFT
Mellum · mradermacher
Params12.1B
Context128K
Q4_K_M8.1 GB
Tool use
ME
Mellum2 12B A2.5B Thinking
Mellum · JetBrains
Params12.1B
Context128K
Smallest7.0 GB
ReasoningTool use
ME
Mellum2 12B A2.5B Thinking
Mellum · mradermacher
Params12.1B
Context128K
Q4_K_M8.1 GB
ReasoningTool use
ME
Mellum2-12B-A2.5B-Instruct
Mellum · Mungert
Params12.1B
Context128K
Q4_K_M8.2 GB
Tool use
ME
Mellum2 12B A2.5B Base
Mellum · mradermacher
Params12.1B
Context128K
Q4_K_M8.1 GB
GGUF
ME
Mellum2.1 12B A2.5B MaxQuality iMatrix
Mellum · offmonreal
Params12.1B
Context128K
Q4_K_M8.1 GB
CodingReasoningTool use
ME
Mellum2.1 12B A2.5B Thinking
Mellum · Ninnix96
Params12.1B
Context128K
Smallest6.3 GB
ReasoningTool use
ME
Mellum2 12B A2.5B Thinking
Mellum · JetBrains
Params12.1B
Context128K
Smallest12.9 GB
ReasoningTool use
ME
Mellum2 12B A2.5B Thinking Abliterated
Mellum · josephmayo
Params12.1B
Context128K
Smallest8.2 GB
Reasoning
ME
Mellum2 12B A2.5B Thinking SFT
Mellum · mradermacher
Params12.1B
Context128K
Q4_K_M8.1 GB
ReasoningTool use
ME
Mellum 4b Dpo Python
Mellum · mradermacher
Params4.02B
Context8K
Q4_K_M2.6 GB
Coding
ME
Mellum2.1 12B A2.5B Thinking
Mellum · Myric
Params12.1B
Context128K
Smallest4.7 GB
CodingReasoningTool use
ME
Mellum2 12B A2.5B Base
Mellum · mradermacher
Params12.1B
Context128K
Q4_K_M8.1 GB
GGUF
ME
Mellum 4b Sft Rust
Mellum · mradermacher
Params4.02B
Context8K
Q4_K_M2.6 GB
Coding

About the Mellum GGUF models

Mellum is represented on ggufmodels.com by 91 GGUF models, quantized by 35 uploaders on Hugging Face. The most downloaded are Mellum2.1-12B-A2.5B-Thinking, Mellum2 12B A2.5B Instruct and Mellum2 12B A2.5B Instruct. Parameter counts run from 833M to 12.6B, and the longest trained context window is 128K tokens.

A Q4_K_M file of a Mellum model is between 0.5 to 9.0 GB, which is the quant most people start with. Most files come from mradermacher (24), JetBrains (17) and kingjones777 (6). The quants you will meet most often are Q4_K_M (57), Q8_0 (50), Q6_K (47) and Q5_K_M (42), where the number is how many models offer that quant.

Frequently asked questions

Which Mellum GGUF should I download?

The most downloaded Mellum GGUF here is Mellum2.1-12B-A2.5B-Thinking. 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 Mellum model need?

Q4_K_M files of Mellum models on this site range from 0.5 to 9.0 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 Mellum GGUF files come from?

The most common quantizers here are mradermacher, JetBrains and kingjones777. 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