CO

cogito v1

CogitoGGUF by cortexsoUpdated 2025-04-10
Download on Hugging Face
Parameters3.61B
Context128K
Layers28
Architecturellama
Smallest quant1.5 GB
Quick answer

cogito v1 needs about 3.7 GB of memory at Q4_K_M (a 2.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 41 quants, from 1.5 GB (Q2_K) to 42.5 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

Cogito v1 – a 3.61B LLaMA‑based model with reasoning and tool use

Cogito v1 is a 3.61B parameter LLaMA architecture model trained with Iterated Distillation and Amplification. It supports reasoning and tool use. The model is released under the Apache‑2.0 license.

Good at

  • Reasoning tasks
  • Tool‑based interactions
  • General LLM usage

Limits

  • No vision support
  • Large context requires high VRAM
  • No Mixture of Experts

Best for

  • Chat assistants
  • Code generation
  • Agentic workflows

Who it’s for. Developers and researchers who need a lightweight reasoning model with tool integration. The model is suitable for local deployment on GPUs with sufficient VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.5 GB 2.9 GB
Fits Get file →
Q3_K_S1.7 GB 3.2 GB
Fits Get file →
Q3_K_M1.9 GB 3.3 GB
Fits Get file →
Q3_K_L2.0 GB 3.4 GB
Fits Get file →
Q4_K_S2.1 GB 3.6 GB
Fits Get file →
Q4_K_M2.2 GB 3.7 GB
Fits Get file →
Q5_K_S2.5 GB 4.0 GB
Fits Get file →
Q5_K_M2.6 GB 4.0 GB
Fits Get file →
Q6_K3.0 GB 4.4 GB
Fits Get file →
Q2_K3.2 GB 4.6 GB
Fits Get file →
Q3_K_S3.7 GB 5.1 GB
Fits Get file →
Q8_03.8 GB 5.3 GB
Fits Get file →
Q3_K_M4.0 GB 5.5 GB
Fits Get file →
Q3_K_L4.3 GB 5.8 GB
Fits Get file →
Q4_K_S4.7 GB 6.1 GB
Fits Get file →
Q4_K_M4.9 GB 6.4 GB
Fits Get file →
Q5_K_S5.6 GB 7.0 GB
Fits Get file →
Q5_K_M5.7 GB 7.2 GB
Fits Get file →
Q2_K5.8 GB 7.2 GB
Tight Get file →
Q6_K6.6 GB 8.0 GB
Too big Get file →
Q3_K_S6.7 GB 8.1 GB
Too big Get file →
Q3_K_M7.3 GB 8.8 GB
Too big Get file →
Q3_K_L7.9 GB 9.4 GB
Too big Get file →
Q8_08.5 GB 10.0 GB
Too big Get file →
Q4_K_S8.6 GB 10.0 GB
Too big Get file →
Q4_K_M9.0 GB 10.4 GB
Too big Get file →
Q5_K_S10.3 GB 11.7 GB
Too big Get file →
Q5_K_M10.5 GB 11.9 GB
Too big Get file →
Q6_K12.1 GB 13.6 GB
Too big Get file →
Q2_K12.3 GB 13.8 GB
Too big Get file →
Q3_K_S14.4 GB 15.8 GB
Too big Get file →
Q8_015.7 GB 17.1 GB
Too big Get file →
Q3_K_M15.9 GB 17.4 GB
Too big Get file →
Q3_K_L17.2 GB 18.7 GB
Too big Get file →
Q4_K_S18.8 GB 20.2 GB
Too big Get file →
Q4_K_M19.8 GB 21.3 GB
Too big Get file →
Q5_K_S22.6 GB 24.1 GB
Too big Get file →
Q5_K_M23.3 GB 24.7 GB
Too big Get file →
Q6_K26.9 GB 28.3 GB
Too big Get file →
Q8_034.8 GB 36.3 GB
Too big Get file →
Q4_K_M42.5 GB 44.0 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (file size 2.24 GB, estimated 3.7 GB memory). For 12 GB VRAM, Q5_K_M (file size 5.73 GB, estimated 7.2 GB memory) is a good balance. For 24 GB VRAM, Q6_K (file size 12.12 GB, estimated 13.6 GB memory) provides higher quality.

What GPU do you need for cogito v1?

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 Q5_K_M (2.6 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q3_K_L (4.3 GB file, about 5.8 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (6.6 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_K_M (10.5 GB file, about 11.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q3_K_S (14.4 GB file, about 15.8 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (19.8 GB file, about 21.3 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (26.9 GB file, about 28.3 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_M (42.5 GB file, about 44.0 GB in use).

Which cogito v1 quant should you choose?

Q4_K_M is the usual starting point for cogito v1: it balances file size and quality well. Here it is a 2.2 GB file.

The Q8_0 file is 3.8 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 Q2_K at 1.5 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

Architecturellama
Parameters3.61B
Layers28
Trained context131,072 tokens
KV cache (fp16)112 KB per token

Source

Quantized bycortexso
FamilyCogito
Licenseapache-2.0
Downloads (HF)956
Last updated2025-04-10

Frequently asked questions about cogito v1

How much VRAM does cogito v1 need?

About 3.7 GB at Q4_K_M with an 8K context window. That is the 2.2 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 v1 on an 8 GB GPU?

Yes, with Q6_K: the 6.6 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of cogito v1 GGUF?

It depends on the quant: Q2_K is 1.5 GB, Q3_K_S is 1.7 GB, Q3_K_M is 1.9 GB, Q3_K_L is 2.0 GB, Q4_K_S is 2.1 GB, Q4_K_M is 2.2 GB and 35 more.

What context length does cogito v1 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.

Where can I download cogito v1 GGUF?

The files are on Hugging Face in the cortexso/cogito-v1 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 v1 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 Cogito v1 on 8 GB VRAM?

Yes, use the Q4_K_M quantized file which requires about 3.7 GB of VRAM at 8k context.

Does Cogito v1 support image inputs?

No, the model has no vision capability.

Similar models

Browse all →

More from cortexso

All by cortexso →

More Cogito models

All Cogito →

Other small models

All small models →