Mellum2 12B A2.5B Instruct needs about 13.9 GB of memory at Q8_0 (a 12.9 GB file) with an 8K context window, so it fits on a 16 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.
Mellum2 12B A2.5B Instruct – a 12 B Mixture‑of‑Experts assistant model
Mellum2 12B A2.5B Instruct is a 12 B parameter model with 2.5 B active experts. It supports a 131,072‑token context and is trained for direct instruction following without a chain of thought. The model is released under Apache 2.0.
Good at
- Direct instruction following
- Interactive chat and code assistance
- Tool‑use scenarios
Limits
- Large VRAM requirement – 13.9 GB at 8 k context
- No vision or multimodal support
- Requires GGUF Q8_0 quantization
Best for
- Chatbot applications needing quick answers
- Code generation and debugging tools
- Instruction‑driven agents
Who it’s for. Developers and researchers building low‑latency chat or coding assistants who need a large context window and Mixture‑of‑Experts architecture. The model is suitable for environments that can host 13 GB of VRAM and support GGUF runtimes.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 12.9 GB | 13.9 GB | Too big | Get file → |
For 8 GB VRAM, the Q8_0 quantization is the only available file and requires approximately 13.9 GB of VRAM at 8 k context. If more VRAM is available, Q8_0 provides the best fidelity to the BF16 model. No other quantizations are listed.
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: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: the best quant that fits is Q8_0 (12.9 GB file, about 13.9 GB in use).
Which Mellum2 12B A2.5B Instruct quant should you choose?
Q8_0 (12.9 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Mellum2 12B A2.5B Instruct
How much VRAM does Mellum2 12B A2.5B Instruct need?
About 13.9 GB at Q8_0 with an 8K context window. That is the 12.9 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?
Not at an 8K context. The smallest file needs about 13.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Mellum2 12B A2.5B Instruct GGUF?
It depends on the quant: Q8_0 is 12.9 GB.
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 JetBrains/Mellum2-12B-A2.5B-Instruct-GGUF-Q8_0 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?
No. The Q8_0 quantization requires about 13.9 GB of VRAM at 8 k context, so 8 GB is insufficient.
Does this model support vision or multimodal inputs?
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.