CA

CAJAL 4B Merged 16bit

CajalGGUF by AgnuxoUpdated 2026-05-10
Download on Hugging Face
Parameters4.21B
Context256K
Layers32
Architectureqwen35
Smallest quant2.7 GB
Quick answer

CAJAL 4B Merged 16bit needs about 4.3 GB of memory at Q4_K_M (a 2.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 2.7 GB (Q4_K_M) to 8.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

CAJAL 4B Merged 16bit – 4B parameter Qwen‑35 model for scientific paper generation

CAJAL 4B Merged 16bit is a 4B parameter Qwen‑35 architecture model trained for scientific paper generation. It is fully local and supports a 262144 token context. The model is released under the Apache‑2.0 license.

Good at

  • Scientific paper generation
  • Code generation in Python, JavaScript, Rust, Go, C++
  • Agent coordination via MCP and A2A

Limits

  • No vision support
  • Large context requires significant VRAM
  • Requires 8k context for memory estimates

Best for

  • Academic writing assistants
  • Scientific code generation
  • Agent‑based task decomposition

Who it’s for. Researchers, developers, and academic teams needing a local model for scientific writing and code generation. The model is suitable for users who prefer open‑source solutions and can manage the required VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M2.7 GB 4.3 GB
Fits Get file →
Q8_04.5 GB 6.1 GB
Fits Get file →
F168.4 GB 10.0 GB
Too big Get file →

For 8 GB VRAM, use the Q4_K_M quantized file (2.71 GB, ~4.3 GB memory at 8k context). For 12 GB VRAM, Q8_0 (4.48 GB, ~6.1 GB memory) is suitable. If more memory is available, the F16 quant (8.42 GB, ~10 GB memory) provides higher precision.

What GPU do you need for CAJAL 4B Merged 16bit?

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 Q4_K_M (2.7 GB file, about 4.3 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.5 GB file, about 6.1 GB in use).
  • 12 GB VRAM: the best quant that fits is F16 (8.4 GB file, about 10.0 GB in use).

Which CAJAL 4B Merged 16bit quant should you choose?

Q4_K_M is the usual starting point for CAJAL 4B Merged 16bit: it balances file size and quality well. Here it is a 2.7 GB file.

The Q8_0 file is 4.5 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters4.21B
Layers32
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized byAgnuxo
FamilyCajal
RepositoryAgnuxo/CAJAL-4B
Licenseapache-2.0
Downloads (HF)3,740
Last updated2026-05-10

Frequently asked questions about CAJAL 4B Merged 16bit

How much VRAM does CAJAL 4B Merged 16bit need?

About 4.3 GB at Q4_K_M with an 8K context window. That is the 2.7 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 CAJAL 4B Merged 16bit on an 8 GB GPU?

Yes, with Q8_0: the 4.5 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of CAJAL 4B Merged 16bit GGUF?

It depends on the quant: Q4_K_M is 2.7 GB, Q8_0 is 4.5 GB, F16 is 8.4 GB.

What context length does CAJAL 4B Merged 16bit support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download CAJAL 4B Merged 16bit GGUF?

The files are on Hugging Face in the Agnuxo/CAJAL-4B repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does CAJAL 4B Merged 16bit 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 CAJAL 4B Merged 16bit on 8 GB VRAM?

Yes, using the Q4_K_M quantized file which requires approximately 4.3 GB memory at 8k context.

Does the model support vision tasks?

No, the model does not have vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Similar models

Browse all →

More from Agnuxo

All by Agnuxo →

More Cajal models

All Cajal →

Other small models

All small models →