Mellum2 12B A2.5B Claude 4.6 4.8 Opus 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. This repository has 4 quants, from 5.0 GB (Q2_K) to 12.9 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.
Mellum2 12B A2.5B Claude 4.6 4.8 Opus Thinking – a Mixture‑of‑Experts reasoning model
Mellum2 12B A2.5B Claude 4.6 4.8 Opus Thinking is a 12.1B parameter model with 2.5B active parameters per token. It uses a 28‑layer Mellum architecture with 64 experts, 8 activated per token, and a context length of 131,072 tokens. The model emits reasoning inside ` ` blocks before the final answer.
Good at
- Step‑by‑step reasoning
- Long‑form math and debugging
- Agentic workflows
Limits
- No vision support
- Requires 8‑k context for memory estimates
- Apache‑2.0 license
Best for
- Complex coding tasks
- Multi‑step planning
- Math‑heavy problem solving
Who it’s for. Developers and researchers who need a local LLM that can perform detailed reasoning and produce clear step‑by‑step explanations. The model is suitable for applications that require long context and explicit chain‑of‑thought generation.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 5.0 GB | 6.0 GB | Fits | Get file → | |
| Q4_K_M | 8.1 GB | 9.0 GB | Too big | Get file → | |
| Q6_K | 10.9 GB | 11.8 GB | Too big | Get file → | |
| Q8_0 | 12.9 GB | 13.9 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 8.07 GB, estimated memory 9 GB at 8 k context). For 12 GB VRAM, Q6_K (10.88 GB, 11.8 GB). For 16 GB VRAM, Q8_0 (12.93 GB, 13.9 GB). Q2_K is the smallest but offers the lowest quality.
What GPU do you need for Mellum2 12B A2.5B Claude 4.6 4.8 Opus 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: the best quant that fits is Q2_K (5.0 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q2_K (5.0 GB file, about 6.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (10.9 GB file, about 11.8 GB in use).
- 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 Claude 4.6 4.8 Opus Thinking quant should you choose?
Q4_K_M is the usual starting point for Mellum2 12B A2.5B Claude 4.6 4.8 Opus Thinking: it balances file size and quality well. Here it is a 8.1 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 Q2_K at 5.0 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Mellum2 12B A2.5B Claude 4.6 4.8 Opus Thinking
How much VRAM does Mellum2 12B A2.5B Claude 4.6 4.8 Opus 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 Claude 4.6 4.8 Opus Thinking on an 8 GB GPU?
Yes, with Q2_K: the 5.0 GB file needs about 6.0 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 Claude 4.6 4.8 Opus Thinking GGUF?
It depends on the quant: Q2_K is 5.0 GB, Q4_K_M is 8.1 GB, Q6_K is 10.9 GB, Q8_0 is 12.9 GB.
What context length does Mellum2 12B A2.5B Claude 4.6 4.8 Opus 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 Claude 4.6 4.8 Opus Thinking GGUF?
The files are on Hugging Face in the yuxinlu1/Mellum2-12B-A2.5B-Claude-4.6-4.8-Opus-Thinking-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 Claude 4.6 4.8 Opus 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 on 8 GB VRAM?
Yes, using the Q4_K_M quant which requires about 9 GB of VRAM at 8 k context.
Does the model support vision?
No, the model is text‑only and does not have vision capabilities.
What license does the model use?
The model is released under the Apache‑2.0 license.