Mellum2 12B A2.5B Thinking 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. Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.
Mellum2 12B A2.5B Thinking – a reasoning‑augmented Mixture‑of‑Experts model
Mellum2 12B A2.5B Thinking is a 12.1‑billion‑parameter model with 2.5 billion active parameters. It uses a 28‑layer architecture, 64 experts with 8 activated per token, and a 131,072‑token context length. The model emits chain‑of‑thought reasoning inside `…` blocks before the final answer.
Good at
- Explicit chain‑of‑thought reasoning
- Complex debugging and multi‑step planning
- Math‑heavy tasks
Limits
- No vision support
- Requires 131,072‑token context for full capability
- Apache 2.0 license restricts commercial redistribution
Best for
- Agents needing reasoning traces
- Long‑form math problem solving
- Debugging complex code
Who it’s for. Developers and researchers who need a text‑only model that provides explicit reasoning steps. It is suitable for building agents that require transparent decision processes.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 8.1 GB | 9.0 GB | Too big | Get file → |
The Q4_K_M quantization is 8.07 GB and needs about 9 GB of VRAM at 8 k context. For 8 GB VRAM, Q4_K_M is the only available quant. If more VRAM is available, consider higher‑precision quants for better quality.
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: 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: the best quant that fits is Q4_K_M (8.1 GB file, about 9.0 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 8.1 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Mellum2 12B A2.5B Thinking
How much VRAM does Mellum2 12B A2.5B Thinking 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 Thinking on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 9.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Mellum2 12B A2.5B Thinking GGUF?
It depends on the quant: Q4_K_M is 8.1 GB.
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 JetBrains/Mellum2-12B-A2.5B-Thinking-GGUF-Q4_K_M 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, the Q4_K_M quantization requires about 9 GB of VRAM at 8 k context, so it will fit on 8 GB with slight memory overhead.
Does this model support image input?
No, it is a text‑only model with no vision capabilities.
What license applies to this model?
It is released under the Apache 2.0 license.