ME

Mellum2.1-12B-A2.5B-Thinking

MellumGGUF by JetBrainsUpdated 2026-10-22
Download on Hugging Face
Parameters12.1B
Context128K
Layers28
Architecturemellum
Smallest quant1.8 GB
Quick answer

Mellum2.1-12B-A2.5B-Thinking needs about 9.0 GB of memory at Q4_K_M (a 8.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 11 quants, from 1.8 GB (BF16) to 25.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

Mellum2.1-12B-A2.5B-Thinking: a 12B Mixture-of-Experts reasoning model

Mellum2.1-12B-A2.5B-Thinking is a 12B parameter model with 2.5B active parameters. It supports a 131,072-token context and is optimized for reasoning tasks. The model is released under Apache 2.0 and is available in multiple GGUF quantizations.

Good at

  • Complex reasoning
  • Agentic code editing
  • Tool‑based problem solving

Limits

  • Requires large VRAM for high‑quality quants
  • No vision support
  • Large context length may need more RAM

Best for

  • Software engineering agents
  • Math and logic puzzles
  • Long‑form reasoning

Who it’s for. Developers and researchers who need a reasoning‑focused LLM with a large context window. The model is suitable for building agents that interact with code repositories and execute shell commands.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
BF161.8 GB 2.7 GB
Fits Get file →
MXFP4_MOE7.0 GB 8.0 GB
Tight Get file →
MXFP4_MOE7.3 GB 8.2 GB
Too big Get file →
Q4_K_M8.1 GB 9.0 GB
Too big Get file →
Q4_K_M8.3 GB 9.3 GB
Too big Get file →
Q6_K10.9 GB 11.8 GB
Too big Get file →
Q6_K11.3 GB 12.2 GB
Too big Get file →
Q8_012.9 GB 13.9 GB
Too big Get file →
Q8_013.4 GB 14.4 GB
Too big Get file →
BF1624.3 GB 25.3 GB
Too big Get file →
BF1625.2 GB 26.1 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (≈9 GB memory at 8 k context). For 12 GB VRAM, Q6_K (≈12 GB). For 16 GB VRAM, Q8_0 (≈14 GB). BF16 variants need 25–26 GB VRAM and are not recommended for limited memory.

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: the best quant that fits is BF16 (1.8 GB file, about 2.7 GB in use).
  • 6 GB VRAM: the best quant that fits is BF16 (1.8 GB file, about 2.7 GB in use).
  • 8 GB VRAM: the best quant that fits is MXFP4_MOE (7.0 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (10.9 GB file, about 11.8 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (13.4 GB file, about 14.4 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (13.4 GB file, about 14.4 GB in use).
  • 32 GB VRAM: the best quant that fits is BF16 (25.2 GB file, about 26.1 GB in use).

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

Q4_K_M is the usual starting point for Mellum2.1-12B-A2.5B-Thinking: it balances file size and quality well. Here it is a 8.1 GB file.

The Q8_0 file is 12.9 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is BF16 at 1.8 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

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 byJetBrains
FamilyMellum
Licenseapache-2.0
Downloads (HF)286,168
Last updated2026-10-22

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 Q4_K_M 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 MXFP4_MOE: the 7.0 GB file needs about 8.0 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: BF16 is 1.8 GB, MXFP4_MOE is 7.0 GB, MXFP4_MOE is 7.3 GB, Q4_K_M is 8.1 GB, Q4_K_M is 8.3 GB, Q6_K is 10.9 GB and 5 more.

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 JetBrains/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, using the Q4_K_M quantization which requires about 9 GB VRAM at 8 k context.

Does the model support image inputs?

No, Mellum2.1 is a text‑only model with no vision capabilities.

What license applies to this model?

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 JetBrains

All by JetBrains →

More Mellum models

All Mellum →

Other medium models

All medium models →