ME

Mellum2.1 12B A2.5B Thinking

MellumGGUF by Ninnix96Updated 2026-10-19
Download on Hugging Face
Parameters12.1B
Context128K
Layers28
Architecturemellum
Smallest quant6.3 GB
Quick answer

Mellum2.1 12B A2.5B Thinking needs about 9.0 GB of memory at Q5_0 (a 8.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 4 quants, from 6.3 GB (IQ3_XXS) to 10.4 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

Mellum2.1 12B A2.5B Thinking – a 12B MoE model for reasoning and tool use

Mellum2.1 12B A2.5B Thinking is a 12.1B parameter mixture‑of‑experts model with 2.5B active parameters. It supports a context length of 131,072 tokens and is trained for complex agentic tasks such as repository work, command execution, and tool calling.

Good at

  • Reasoning
  • Tool use
  • Agentic code editing

Limits

  • No vision support
  • Requires large VRAM for full precision
  • License is Apache‑2.0

Best for

  • Software engineering agents
  • Complex math and coding tasks
  • Tool‑driven workflows

Who it’s for. Developers and researchers needing a model that can reason, call tools, and edit code within real repositories. The model is suitable for sandboxed agentic experiments and advanced coding assistance.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_XXS6.3 GB 7.2 GB
Tight Get file →
Q5_08.1 GB 9.0 GB
Too big Get file →
Q5_09.0 GB 9.9 GB
Too big Get file →
—10.4 GB 11.3 GB
Too big Get file →

For 8 GB VRAM, use the IQ3_XXS quant (6.26 GB file, ~7.2 GB memory at 8 k context). For 12 GB VRAM, Q5_0 (8.05 GB file, ~9 GB memory) is a good balance. If 16 GB VRAM is available, the larger Q5_0 (8.98 GB file, ~9.9 GB memory) offers higher quality.

What GPU do you need for Mellum2.1 12B A2.5B Thinking?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: the best quant that fits is IQ3_XXS (6.3 GB file, about 7.2 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (10.4 GB file, about 11.3 GB in use).

Which Mellum2.1 12B A2.5B Thinking quant should you choose?

Q5_0 (8.1 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

If memory is tight, the smallest file is IQ3_XXS at 6.3 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturemellum
Parameters12.1B (approximate, mixture of experts)
Active parameters2.5B
Layers28
Trained context131,072 tokens
KV cache (fp16)56 KB per token

Source

Quantized byNinnix96
FamilyMellum
Licenseapache-2.0
Downloads (HF)621
Last updated2026-10-19

Frequently asked questions about Mellum2.1 12B A2.5B Thinking

How much VRAM does Mellum2.1 12B A2.5B Thinking need?

About 9.0 GB at Q5_0 with an 8K context window. That is the 8.1 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Mellum2.1 12B A2.5B Thinking on an 8 GB GPU?

Yes, with IQ3_XXS: the 6.3 GB file needs about 7.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Mellum2.1 12B A2.5B Thinking GGUF?

It depends on the quant: IQ3_XXS is 6.3 GB, Q5_0 is 8.1 GB, Q5_0 is 9.0 GB, file is 10.4 GB.

What context length does Mellum2.1 12B A2.5B Thinking support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.

Where can I download Mellum2.1 12B A2.5B Thinking GGUF?

The files are on Hugging Face in the Ninnix96/Mellum2.1-12B-A2.5B-Thinking-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Mellum2.1 12B A2.5B Thinking use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Mellum2.1 on 8 GB VRAM?

Yes, the IQ3_XXS quant file is 6.26 GB and requires about 7.2 GB of VRAM at 8 k context.

Does the model support vision?

No, the model does not have vision capabilities.

What license does it use?

The model is released under the Apache‑2.0 license.

Other GGUFs of Mellum2.1-12B-A2.5B-Thinking

Similar models

Browse all →

More from Ninnix96

All by Ninnix96 →

More Mellum models

All Mellum →

Other medium models

All medium models →