Mellum2 12B A2.5B Instruct SFT 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 Instruct SFT – a 12.1B parameter Mixture‑of‑Experts model
Mellum2 12B A2.5B Instruct SFT is a 12.1B parameter model with 2.5B active parameters. It uses a Mixture‑of‑Experts architecture with 64 experts, activating 8 per token. The context length is 131,072 tokens.
Good at
- Tool use
- Instruction following
- Large context handling
Limits
- No vision support
- Requires high VRAM for full precision
- Apache‑2.0 license
Best for
- Research on SFT stage
- Post‑training experiments
- Comparing against RL‑tuned variants
Who it’s for. Researchers and developers who need a supervised‑fine‑tuned checkpoint of the Mellum2 family. It is useful for studying the SFT stage or building on it before RL‑tuning.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.0 GB | Fits | Get file → | |
| IQ1_S | 3.9 GB | 4.9 GB | Fits | Get file → | |
| IQ1_M | 4.1 GB | 5.1 GB | Fits | Get file → | |
| IQ2_XXS | 4.4 GB | 5.4 GB | Fits | Get file → | |
| IQ2_XS | 4.7 GB | 5.6 GB | Fits | Get file → | |
| IQ2_S | 4.7 GB | 5.7 GB | Fits | Get file → | |
| IQ2_M | 5.0 GB | 5.9 GB | Fits | Get file → | |
| Q2_K | 5.0 GB | 6.0 GB | Fits | Get file → | |
| Q2_K_S | 5.0 GB | 6.0 GB | Fits | Get file → | |
| IQ3_XXS | 5.4 GB | 6.4 GB | Fits | Get file → | |
| IQ3_XS | 5.5 GB | 6.5 GB | Fits | Get file → | |
| Q3_K_S | 5.8 GB | 6.8 GB | Fits | Get file → | |
| IQ3_S | 5.8 GB | 6.8 GB | Fits | Get file → | |
| IQ3_M | 5.9 GB | 6.9 GB | Fits | Get file → | |
| Q3_K_M | 6.3 GB | 7.3 GB | Tight | Get file → | |
| Q3_K_L | 6.6 GB | 7.6 GB | Tight | Get file → | |
| IQ4_XS | 6.7 GB | 7.6 GB | Tight | Get file → | |
| IQ4_NL | 6.9 GB | 7.9 GB | Tight | Get file → | |
| Q4_0 | 6.9 GB | 7.9 GB | Tight | Get file → | |
| Q4_K_S | 7.4 GB | 8.4 GB | Too big | Get file → | |
| Q4_1 | 7.7 GB | 8.6 GB | Too big | Get file → | |
| Q4_K_M | 8.1 GB | 9.0 GB | Too big | Get file → | |
| Q5_K_S | 8.6 GB | 9.6 GB | Too big | Get file → | |
| Q5_K_M | 9.2 GB | 10.2 GB | Too big | Get file → | |
| Q6_K | 10.9 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 Q4_K_M (file size 8.07 GB, memory 9 GB). For 16 GB VRAM, use Q5_K_M (file size 9.21 GB, memory 10.2 GB). Memory estimates are approximate.
What GPU do you need for Mellum2 12B A2.5B Instruct SFT?
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 Instruct SFT quant should you choose?
Q4_K_M is the usual starting point for Mellum2 12B A2.5B Instruct SFT: 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
Source
Frequently asked questions about Mellum2 12B A2.5B Instruct SFT
How much VRAM does Mellum2 12B A2.5B Instruct SFT 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 Instruct SFT 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 Instruct SFT 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 Instruct SFT 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 SFT GGUF?
The files are on Hugging Face in the mradermacher/Mellum2-12B-A2.5B-Instruct-SFT-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 Instruct SFT 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, use the IQ1_S quant which requires about 4.9 GB of VRAM at 8 k context.
Does this 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.