LL

Cogito-V2-Preview-Llama-109B-Moe

LlamaGGUF by unslothUpdated 2025-07-31
Download on Hugging Face
Parameters108B
Context256K
Layers48
Architecturellama4
Smallest quant30.0 GB
Quick answer

Cogito-V2-Preview-Llama-109B-Moe needs about 67.5 GB of memory at Q4_K_M (a 65.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 27 quants, from 30.0 GB (TQ1_0) to 215.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

Cogito‑V2‑Preview‑Llama‑109B‑MoE – a 109B Mixture‑of‑Experts LLM with vision and long‑context support

Cogito‑V2‑Preview‑Llama‑109B‑MoE is a 109B‑parameter LLM that uses a mixture‑of‑experts architecture. It supports up to 262144‑token contexts and includes vision capabilities. The model is instruction tuned and optimized for coding, STEM, and multilingual use.

Good at

  • Long‑context reasoning
  • Vision‑enabled tasks
  • Multilingual instruction following

Limits

  • Requires large VRAM for full precision
  • No native vision support in llama.cpp without custom code
  • License is llama4 – commercial use allowed

Best for

  • Code generation with long context
  • Multilingual document summarization
  • Vision‑based question answering

Who it’s for. Developers and researchers needing a large, hybrid reasoning model with vision support and extensive context length. The model is suitable for applications that require detailed, multi‑step reasoning and multilingual capabilities.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
TQ1_030.0 GB 32.1 GB
Too big Get file →
IQ1_S33.0 GB 35.1 GB
Too big Get file →
IQ1_M35.7 GB 37.8 GB
Too big Get file →
IQ2_XXS38.5 GB 40.6 GB
Too big Get file →
Q2_K39.6 GB 41.7 GB
Too big Get file →
Q2_K_L39.8 GB 41.9 GB
Too big Get file →
IQ2_M39.9 GB 42.1 GB
Too big Get file →
Q2_K_XL43.0 GB 45.1 GB
Too big Get file →
IQ3_XXS46.5 GB 48.6 GB
Too big Get file →
Q3_K_S46.7 GB 48.8 GB
Too big Get file →
Q3_K_XL49.6 GB 51.7 GB
Too big Get file →
Q3_K_M51.7 GB (2 parts) 53.9 GB
Too big Get file →
IQ4_XS57.6 GB (2 parts) 59.8 GB
Too big Get file →
IQ4_NL60.9 GB (2 parts) 63.1 GB
Too big Get file →
Q4_061.2 GB (2 parts) 63.3 GB
Too big Get file →
Q4_K_S61.4 GB (2 parts) 63.6 GB
Too big Get file →
Q4_K_XL62.4 GB (2 parts) 64.5 GB
Too big Get file →
Q4_K_M65.4 GB (2 parts) 67.5 GB
Too big Get file →
Q4_167.6 GB (2 parts) 69.7 GB
Too big Get file →
Q5_K_S74.2 GB (2 parts) 76.4 GB
Too big Get file →
Q5_K_M76.5 GB (2 parts) 78.6 GB
Too big Get file →
Q5_K_XL79.2 GB (2 parts) 81.3 GB
Too big Get file →
Q6_K88.4 GB (2 parts) 90.5 GB
Too big Get file →
Q6_K_XL94.1 GB (2 parts) 96.2 GB
Too big Get file →
Q8_0114.5 GB (3 parts) 116.6 GB
Too big Get file →
Q8_K_XL128.2 GB (3 parts) 130.3 GB
Too big Get file →
BF16215.5 GB (5 parts) 217.7 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_S (file size 61.45 GB, estimated 63.6 GB memory at 8 k context). For 12 GB VRAM, Q4_K_M (65.35 GB, 67.5 GB memory) is a good balance. For 24 GB VRAM, Q4_K_XL (62.36 GB, 64.5 GB memory) provides higher quality with acceptable memory usage.

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: 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: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: the best quant that fits is Q2_K_XL (43.0 GB file, about 45.1 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 65.4 GB file.

The Q8_0 file is 114.5 GB, about 1.8 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 TQ1_0 at 30.0 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama4
Parameters108B (approximate, mixture of experts)
Layers48
Trained context262,144 tokens
KV cache (fp16)192 KB per token

Source

Quantized byunsloth
FamilyLlama
Licensellama4
Downloads (HF)1,587
Last updated2025-07-31

Frequently asked questions about Cogito-V2-Preview-Llama-109B-Moe

How much VRAM does Cogito-V2-Preview-Llama-109B-Moe need?

About 67.5 GB at Q4_K_M with an 8K context window. That is the 65.4 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?

Not at an 8K context. The smallest file needs about 32.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Cogito-V2-Preview-Llama-109B-Moe GGUF?

It depends on the quant: TQ1_0 is 30.0 GB, IQ1_S is 33.0 GB, IQ1_M is 35.7 GB, IQ2_XXS is 38.5 GB, Q2_K is 39.6 GB, Q2_K_L is 39.8 GB and 21 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 unsloth/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?

Only with a low‑precision quant like Q4_K_S; it will still use around 63.6 GB of VRAM at 8 k context, so 8 GB is insufficient.

Does this model support vision in llama.cpp?

Vision support is detected, but llama.cpp requires custom integration; the base GGUF does not include a vision head.

What is the maximum context length?

The model supports up to 262144 tokens, which is roughly 10 M tokens as noted in the parent card.

Other GGUFs of cogito-v2-preview-llama-109B-MoE

Similar models

Browse all →

More from unsloth

All by unsloth →

More Llama models

All Llama →

Other large models

All large models →