ME

Mellum2 12B A2.5B Thinking

MellumGGUF by bartowskiUpdated 2026-06-10
Download on Hugging Face
Parameters12.1B
Context128K
Layers28
Architecturemellum
Smallest quant0.0 GB
Quick answer

Mellum2 12B A2.5B Thinking needs about 9.1 GB of memory at Q4_K_M (a 8.2 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 27 quants, from 0.0 GB to 24.3 GB (BF16). 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 12.1 B parameter model with a 2.5 B 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
  • Complex debugging and multi‑step planning
  • Math‑heavy tasks

Limits

  • No vision support
  • Requires large VRAM for high‑quality quants
  • No native tool calling

Best for

  • Developers building reasoning agents
  • Researchers testing long‑form reasoning
  • Educators needing step‑by‑step explanations

Who it’s for. This model is suited for users who need detailed reasoning traces before an answer. It is ideal for developers and researchers working on complex problem solving and educational tools that require transparent logic.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.0 GB
Fits Get file →
IQ2_XS4.8 GB 5.8 GB
Fits Get file →
IQ2_S4.9 GB 5.8 GB
Fits Get file →
IQ2_M5.1 GB 6.1 GB
Fits Get file →
Q2_K5.2 GB 6.1 GB
Fits Get file →
Q2_K_L5.4 GB 6.4 GB
Fits Get file →
IQ3_XXS5.8 GB 6.8 GB
Fits Get file →
Q3_K_S5.9 GB 6.9 GB
Fits Get file →
IQ3_XS6.2 GB 7.1 GB
Fits Get file →
Q3_K_M6.2 GB 7.1 GB
Fits Get file →
Q3_K_L6.3 GB 7.2 GB
Tight Get file →
IQ3_M6.3 GB 7.3 GB
Tight Get file →
Q3_K_XL6.5 GB 7.4 GB
Tight Get file →
IQ4_XS6.8 GB 7.7 GB
Tight Get file →
Q4_07.0 GB 8.0 GB
Tight Get file →
IQ4_NL7.0 GB 8.0 GB
Tight Get file →
Q4_K_S7.6 GB 8.5 GB
Too big Get file →
Q4_17.7 GB 8.7 GB
Too big Get file →
Q4_K_M8.2 GB 9.1 GB
Too big Get file →
Q4_K_L8.3 GB 9.3 GB
Too big Get file →
Q5_K_S8.7 GB 9.6 GB
Too big Get file →
Q5_K_M9.3 GB 10.3 GB
Too big Get file →
Q5_K_L9.4 GB 10.4 GB
Too big Get file →
Q6_K11.0 GB 12.0 GB
Too big Get file →
Q6_K_L11.1 GB 12.1 GB
Too big Get file →
Q8_012.9 GB 13.9 GB
Too big Get file →
BF1624.3 GB 25.3 GB
Too big Get file →

For 8 GB VRAM, use IQ2_XS or IQ2_S (≈5.8 GB memory). With 12 GB VRAM, Q4_K_M or Q4_K_L (≈9.1 GB or 9.3 GB) are good choices. For the highest quality, Q8_0 (≈13.9 GB) or BF16 (≈25.3 GB) provide full precision.

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 IQ2_S (4.9 GB file, about 5.8 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ4_NL (7.0 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (11.0 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (12.9 GB file, about 13.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (12.9 GB file, about 13.9 GB in use).
  • 32 GB VRAM: the best quant that fits is BF16 (24.3 GB file, about 25.3 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 8.2 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 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 bybartowski
FamilyMellum
Licenseapache-2.0
Downloads (HF)2,343
Last updated2026-06-10

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

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

About 9.1 GB at Q4_K_M with an 8K context window. That is the 8.2 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 IQ4_NL: 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 12B A2.5B Thinking GGUF?

It depends on the quant: file is 0.0 GB, IQ2_XS is 4.8 GB, IQ2_S is 4.9 GB, IQ2_M is 5.1 GB, Q2_K is 5.2 GB, Q2_K_L is 5.4 GB and 21 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 bartowski/Mellum2-12B-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 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 12B A2.5B Thinking on 8 GB VRAM?

Yes, using the IQ2_XS or IQ2_S quantization, which requires about 5.8 GB of VRAM at 8k context.

Does this model support vision or image input?

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 bartowski

All by bartowski →

More Mellum models

All Mellum →

Other medium models

All medium models →