ME

Mellum2 12B A2.5B Thinking

MellumGGUF by mradermacherUpdated 2026-06-05
Download on Hugging Face
Parameters12.1B
Context128K
Layers28
Architecturemellum
Smallest quant0.0 GB
Quick answer

Mellum2 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 25 quants, from 0.0 GB to 10.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

Mellum2 12B A2.5B Thinking – a reasoning‑augmented LLM

Mellum2 12B A2.5B Thinking is a 12.1B parameter model with a 2.5B active MoE. It supports a 131,072 token context and emits chain‑of‑thought reasoning inside `` blocks. The model is released under Apache 2.0.

Good at

  • Explicit chain‑of‑thought reasoning
  • Multi‑step planning
  • Tool‑aware tasks

Limits

  • Large context length requires high VRAM
  • No vision support
  • Requires 8,000 token context for memory estimates

Best for

  • Debugging complex code
  • Long‑form math problem solving
  • Agentic workflow design

Who it’s for. Developers and researchers needing explicit reasoning traces in a text‑only LLM. The model is suitable for applications that benefit from step‑by‑step explanations before final answers.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.0 GB
Fits Get file →
IQ1_S3.9 GB 4.9 GB
Fits Get file →
IQ1_M4.1 GB 5.1 GB
Fits Get file →
IQ2_XXS4.4 GB 5.4 GB
Fits Get file →
IQ2_XS4.7 GB 5.6 GB
Fits Get file →
IQ2_S4.7 GB 5.7 GB
Fits Get file →
IQ2_M5.0 GB 5.9 GB
Fits Get file →
Q2_K5.0 GB 6.0 GB
Fits Get file →
Q2_K_S5.0 GB 6.0 GB
Fits Get file →
IQ3_XXS5.4 GB 6.4 GB
Fits Get file →
IQ3_XS5.5 GB 6.5 GB
Fits Get file →
Q3_K_S5.8 GB 6.8 GB
Fits Get file →
IQ3_S5.8 GB 6.8 GB
Fits Get file →
IQ3_M5.9 GB 6.9 GB
Fits Get file →
Q3_K_M6.3 GB 7.3 GB
Tight Get file →
Q3_K_L6.6 GB 7.6 GB
Tight Get file →
IQ4_XS6.7 GB 7.6 GB
Tight Get file →
IQ4_NL6.9 GB 7.9 GB
Tight Get file →
Q4_06.9 GB 7.9 GB
Tight Get file →
Q4_K_S7.4 GB 8.4 GB
Too big Get file →
Q4_17.7 GB 8.6 GB
Too big Get file →
Q4_K_M8.1 GB 9.0 GB
Too big Get file →
Q5_K_S8.6 GB 9.6 GB
Too big Get file →
Q5_K_M9.2 GB 10.2 GB
Too big Get file →
Q6_K10.9 GB 11.8 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (file size 3.92 GB, memory 4.9 GB). For 12 GB VRAM, use Q3_K_M (file size 6.33 GB, memory 7.3 GB). For 16 GB VRAM, use Q5_K_M (file size 9.21 GB, memory 10.2 GB). Estimates are approximate.

What GPU do you need for Mellum2 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 the main file (0.0 GB file, about 1.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q2_K_S (5.0 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q4_0 (6.9 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (10.9 GB file, about 11.8 GB in use).

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

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

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

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 bymradermacher
FamilyMellum
Licenseapache-2.0
Downloads (HF)821
Last updated2026-06-05

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

How much VRAM does Mellum2 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 12B A2.5B Thinking on an 8 GB GPU?

Yes, with Q4_0: the 6.9 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

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

It depends on the quant: file is 0.0 GB, IQ1_S is 3.9 GB, IQ1_M is 4.1 GB, IQ2_XXS is 4.4 GB, IQ2_XS is 4.7 GB, IQ2_S is 4.7 GB and 19 more.

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

The files are on Hugging Face in the mradermacher/Mellum2-12B-A2.5B-Thinking-i1-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 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 this model on 8 GB VRAM?

Yes, the IQ1_S quant requires about 4.9 GB of VRAM at 8,000 token context.

Does the model support vision?

No, the model is text‑only and does not include vision capabilities.

What license applies to this model?

The model is released under the Apache 2.0 license.

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

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Mellum models

All Mellum →

Other medium models

All medium models →