Cogito v2 Preview Llama 109B MoE needs about 69.8 GB of memory at Q4_K_M (a 67.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 25 quants, from 0.1 GB to 114.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.
Cogito v2 Preview Llama 109B MoE – a large hybrid reasoning model
Cogito v2 Preview Llama 109B MoE is a 108 billion‑parameter LLM with mixture‑of‑experts architecture. It supports up to 262 144 context tokens and is tuned for coding, STEM, instruction following and tool calling. The model is released under an open license for commercial use.
Good at
- Hybrid reasoning and standard answering
- Coding and STEM tasks
- Tool calling and instruction following
Limits
- Requires large VRAM for full precision
- No vision support
- Long context may increase memory usage
Best for
- Developers building advanced coding assistants
- Researchers testing hybrid reasoning models
- Teams needing multilingual, tool‑aware LLMs
Who it’s for. Engineers and researchers who need a high‑capacity LLM with reasoning capabilities and extensive context support. The model is suitable for commercial applications that can accommodate its memory demands.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.1 GB | 2.2 GB | Fits | Get file → | |
| IQ1_M | 25.7 GB | 27.8 GB | Too big | Get file → | |
| IQ2_XXS | 28.3 GB | 30.5 GB | Too big | Get file → | |
| IQ2_XS | 32.1 GB | 34.2 GB | Too big | Get file → | |
| IQ2_S | 32.3 GB | 34.5 GB | Too big | Get file → | |
| IQ2_M | 36.2 GB | 38.3 GB | Too big | Get file → | |
| Q2_K | 41.5 GB | 43.6 GB | Too big | Get file → | |
| Q2_K_L | 42.5 GB | 44.6 GB | Too big | Get file → | |
| IQ3_XXS | 45.9 GB | 48.0 GB | Too big | Get file → | |
| IQ3_XS | 47.6 GB | 49.7 GB | Too big | Get file → | |
| Q3_K_S | 49.9 GB (2 parts) | 52.0 GB | Too big | Get file → | |
| IQ3_M | 52.1 GB (2 parts) | 54.2 GB | Too big | Get file → | |
| Q3_K_M | 52.1 GB (2 parts) | 54.2 GB | Too big | Get file → | |
| Q3_K_L | 53.8 GB (2 parts) | 55.9 GB | Too big | Get file → | |
| Q3_K_XL | 54.7 GB (2 parts) | 56.8 GB | Too big | Get file → | |
| IQ4_XS | 60.0 GB (2 parts) | 62.1 GB | Too big | Get file → | |
| IQ4_NL | 63.1 GB (2 parts) | 65.2 GB | Too big | Get file → | |
| Q4_0 | 63.9 GB (2 parts) | 66.0 GB | Too big | Get file → | |
| Q4_K_S | 65.1 GB (2 parts) | 67.2 GB | Too big | Get file → | |
| Q4_K_M | 67.7 GB (2 parts) | 69.8 GB | Too big | Get file → | |
| Q4_1 | 69.2 GB (2 parts) | 71.3 GB | Too big | Get file → | |
| Q5_K_S | 75.9 GB (2 parts) | 78.0 GB | Too big | Get file → | |
| Q5_K_M | 78.8 GB (2 parts) | 80.9 GB | Too big | Get file → | |
| Q6_K | 89.9 GB (3 parts) | 92.1 GB | Too big | Get file → | |
| Q8_0 | 114.5 GB (3 parts) | 116.6 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_M (file size 25.74 GB, memory 27.8 GB at 8k context). For 16 GB VRAM, IQ2_XS (32.08 GB, 34.2 GB) or IQ2_S (32.34 GB, 34.5 GB). For 24 GB VRAM, Q2_K (41.53 GB, 43.6 GB) or Q2_K_L (42.54 GB, 44.6 GB).
What GPU do you need for Cogito v2 Preview Llama 109B MoE?
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 (0.1 GB file, about 2.2 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 2.2 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 2.2 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 2.2 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 2.2 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 2.2 GB in use).
- 32 GB VRAM: the best quant that fits is IQ2_XXS (28.3 GB file, about 30.5 GB in use).
- 48 GB VRAM: the best quant that fits is IQ3_XXS (45.9 GB file, about 48.0 GB in use).
Which Cogito v2 Preview Llama 109B MoE quant should you choose?
Q4_K_M is the usual starting point for Cogito v2 Preview Llama 109B MoE: it balances file size and quality well. Here it is a 67.7 GB file.
The Q8_0 file is 114.5 GB, about 1.7 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 the first one in the table at 0.1 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
Frequently asked questions about Cogito v2 Preview Llama 109B MoE
How much VRAM does Cogito v2 Preview Llama 109B MoE need?
About 69.8 GB at Q4_K_M with an 8K context window. That is the 67.7 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 Cogito v2 Preview Llama 109B MoE on an 8 GB GPU?
Yes, with the smaller files: the 0.1 GB file needs about 2.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Cogito v2 Preview Llama 109B MoE GGUF?
It depends on the quant: file is 0.1 GB, IQ1_M is 25.7 GB, IQ2_XXS is 28.3 GB, IQ2_XS is 32.1 GB, IQ2_S is 32.3 GB, IQ2_M is 36.2 GB and 19 more.
What context length does Cogito v2 Preview Llama 109B MoE support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.
Where can I download Cogito v2 Preview Llama 109B MoE GGUF?
The files are on Hugging Face in the bartowski/deepcogito_cogito-v2-preview-llama-109B-MoE-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 Cogito v2 Preview Llama 109B MoE use?
Hugging Face lists the license as llama4. 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?
Use the IQ1_M quant, which estimates 27.8 GB memory at 8k context, so it will not fit on 8 GB VRAM. A smaller quant such as IQ1_M is still too large; you would need at least 16 GB VRAM.
Does this model support vision?
No, the model does not include vision capabilities.
What is the maximum context length?
The model supports up to 262 144 tokens of context.