CA

CatunaMayo3B

CatunamayoGGUF by mradermacherUpdated 2024-05-31
Download on Hugging Face
Parameters3.97B
Context32K
Layers17
Architecturellama
Smallest quant1.5 GB
Quick answer

CatunaMayo3B needs about 3.5 GB of memory at Q4_K_M (a 2.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 15 quants, from 1.5 GB (Q2_K) to 7.9 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.3 GB.

CatunaMayo3B – 3.97B llama model in GGUF format

CatunaMayo3B is a 3.97B parameter llama model merged from multiple Catuna variants. It is available in a range of GGUF quantizations and supports a 32768 token context window. The model is released under the apache-2.0 license.

Good at

  • Large context handling
  • Flexible quantization options
  • Open-source licensing

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • No mixture of experts

Best for

  • Chat applications needing long context
  • Fine-tuning on custom data
  • Research on llama architectures

Who it’s for. Developers and researchers who need a llama model with a large context window and a variety of quantization choices. The model is suitable for local deployment with GGUF and llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.5 GB 2.6 GB
Fits Get file →
IQ3_XS1.7 GB 2.8 GB
Fits Get file →
Q3_K_S1.8 GB 2.8 GB
Fits Get file →
IQ3_S1.8 GB 2.8 GB
Fits Get file →
IQ3_M1.8 GB 2.9 GB
Fits Get file →
Q3_K_M1.9 GB 3.0 GB
Fits Get file →
Q3_K_L2.1 GB 3.2 GB
Fits Get file →
IQ4_XS2.2 GB 3.2 GB
Fits Get file →
Q4_K_S2.3 GB 3.4 GB
Fits Get file →
Q4_K_M2.4 GB 3.5 GB
Fits Get file →
Q5_K_S2.7 GB 3.8 GB
Fits Get file →
Q5_K_M2.8 GB 3.9 GB
Fits Get file →
Q6_K3.3 GB 4.3 GB
Fits Get file →
Q8_04.2 GB 5.3 GB
Fits Get file →
F167.9 GB 9.0 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (file size 2.41 GB, estimated 3.5 GB memory) or Q5_K_S (2.75 GB, 3.8 GB memory). For 4 GB VRAM, Q3_K_M (1.95 GB, 3 GB memory) or Q3_K_S (1.76 GB, 2.8 GB memory) are recommended. For larger VRAM, higher precision quants like Q6_K or Q8_0 provide better quality.

What GPU do you need for CatunaMayo3B?

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 (2.8 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (4.2 GB file, about 5.3 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.2 GB file, about 5.3 GB in use).
  • 12 GB VRAM: the best quant that fits is F16 (7.9 GB file, about 9.0 GB in use).

Which CatunaMayo3B quant should you choose?

Q4_K_M is the usual starting point for CatunaMayo3B: it balances file size and quality well. Here it is a 2.4 GB file.

The Q8_0 file is 4.2 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
Parameters3.97B
Layers17
Trained context32,768 tokens
KV cache (fp16)68 KB per token

Source

Quantized bymradermacher
Licenseapache-2.0
Downloads (HF)1,380
Last updated2024-05-31

Frequently asked questions about CatunaMayo3B

How much VRAM does CatunaMayo3B need?

About 3.5 GB at Q4_K_M with an 8K context window. That is the 2.4 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 CatunaMayo3B on an 8 GB GPU?

Yes, with Q8_0: the 4.2 GB file needs about 5.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of CatunaMayo3B GGUF?

It depends on the quant: Q2_K is 1.5 GB, IQ3_XS is 1.7 GB, Q3_K_S is 1.8 GB, IQ3_S is 1.8 GB, IQ3_M is 1.8 GB, Q3_K_M is 1.9 GB and 9 more.

What context length does CatunaMayo3B support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.6 GB at 8K and 2.3 GB at 32K.

Where can I download CatunaMayo3B GGUF?

The files are on Hugging Face in the mradermacher/CatunaMayo3B-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 CatunaMayo3B 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 CatunaMayo3B on 8 GB VRAM?

Yes, using Q4_K_M or Q5_K_S quants will fit within 8 GB VRAM with estimated memory usage of 3.5 GB or 3.8 GB respectively.

Does CatunaMayo3B support vision tasks?

No, the model does not include vision capabilities.

What license applies to CatunaMayo3B?

The model is released under the apache-2.0 license.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Catunamayo models

All Catunamayo →

Other small models

All small models →