ME

Mellum2 12B A2.5B Instruct

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 Instruct 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 Instruct – a 12B Mixture‑of‑Experts LLM with 131k token context

Mellum2 12B A2.5B Instruct is a 12‑billion‑parameter instruction model built on a Mixture‑of‑Experts architecture. It supports a 131,072‑token context window and is optimized for direct, low‑latency responses in chat, coding, and tool‑use scenarios.

Good at

  • Direct instruction following
  • Code assistance
  • Tool‑use integration

Limits

  • Large VRAM requirement for higher‑quality quants
  • No native vision support
  • Apache‑2.0 license limits commercial use without attribution

Best for

  • Interactive chat bots
  • Rapid code generation
  • Tool‑enabled workflows

Who it’s for. Developers and researchers needing a fast, instruction‑oriented LLM with a very long context window. The model is suitable for applications that require direct answers without a chain of thought.

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 Q4_0 (8 GB file, ~8 GB memory at 8 k context). For 12 GB VRAM, Q4_K_M (8.17 GB file, ~9.1 GB memory) or Q5_K_S (8.67 GB file, ~9.6 GB memory). For 16 GB VRAM, Q6_K (10.99 GB file, ~12 GB memory) provides higher quality. All estimates are approximate.

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

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 Instruct quant should you choose?

Q4_K_M is the usual starting point for Mellum2 12B A2.5B Instruct: 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)3,792
Last updated2026-06-10

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

How much VRAM does Mellum2 12B A2.5B Instruct 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 Instruct 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 Instruct 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 Instruct 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 Instruct GGUF?

The files are on Hugging Face in the bartowski/Mellum2-12B-A2.5B-Instruct-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 Instruct 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 Instruct on 8 GB VRAM?

Yes, using the Q4_0 quantization which requires about 8 GB of VRAM at 8 k context.

Does this model support image input?

No, Mellum2 12B A2.5B Instruct is text‑only and does not have vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license, which allows free use with attribution.

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

Similar models

Browse all →

More from bartowski

All by bartowski →

More Mellum models

All Mellum →

Other medium models

All medium models →