ME

Mellum2 12B A2.5B Thinking Dflash GGUF FIXED

MellumGGUF by rpatel622Updated 2026-07-14
Download on Hugging Face
Parameters833M
Context128K
Layers5
Architecturedflash-draft
Smallest quant0.5 GB
Quick answer

Mellum2 12B A2.5B Thinking Dflash GGUF FIXED needs about 1.1 GB of memory at Q4_K_M (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 0.5 GB (Q4_K_M) to 1.7 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.3 GB.

Mellum2 12B A2.5B Thinking Dflash GGUF FIXED is a 833M-parameter Mellum model in GGUF format, quantized by rpatel622. Its trained context length is 128K tokens. The repository has 5 quant files, from 0.5 GB (Q4_K_M) to 1.7 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M0.5 GB 1.1 GB
Fits Get file →
Q5_K_S0.6 GB 1.2 GB
Fits Get file →
Q8_00.9 GB 1.5 GB
Fits Get file →
BF161.7 GB 2.3 GB
Fits Get file →
F161.7 GB 2.3 GB
Fits Get file →

What GPU do you need for Mellum2 12B A2.5B Thinking Dflash GGUF FIXED?

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 (1.7 GB file, about 2.3 GB in use).

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

Q4_K_M is the usual starting point for Mellum2 12B A2.5B Thinking Dflash GGUF FIXED: it balances file size and quality well. Here it is a 0.5 GB file.

The Q8_0 file is 0.9 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturedflash-draft
Parameters833M
Layers5
Trained context131,072 tokens
KV cache (fp16)10 KB per token

Source

Quantized byrpatel622
FamilyMellum
Licenseapache-2.0
Downloads (HF)162
Last updated2026-07-14

Frequently asked questions about Mellum2 12B A2.5B Thinking Dflash GGUF FIXED

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

About 1.1 GB at Q4_K_M with an 8K context window. That is the 0.5 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 Dflash GGUF FIXED on an 8 GB GPU?

Yes, with BF16: the 1.7 GB file needs about 2.3 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 Dflash GGUF FIXED GGUF?

It depends on the quant: Q4_K_M is 0.5 GB, Q5_K_S is 0.6 GB, Q8_0 is 0.9 GB, BF16 is 1.7 GB, F16 is 1.7 GB.

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

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.3 GB at 32K.

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

The files are on Hugging Face in the rpatel622/Mellum2-12B-A2.5B-Thinking-Dflash-GGUF-FIXED 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 Dflash GGUF FIXED 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.

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

Similar models

Browse all →

More from rpatel622

All by rpatel622 →

More Mellum models

All Mellum →

Other tiny models

All tiny models →