CA

CataLlama-v0.2-Instruct-SFT

CatallamaGGUF by mradermacherUpdated 2025-04-01
Download on Hugging Face
Parameters8.03B
Context8K
Layers32
Architecturellama
Smallest quant3.2 GB
Quick answer

CataLlama-v0.2-Instruct-SFT needs about 6.5 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 15 quants, from 3.2 GB (Q2_K) to 16.1 GB (F16).

CataLlama‑v0.2‑Instruct‑SFT – 8.03B Llama‑3 based instruction model in Catalan

CataLlama‑v0.2‑Instruct‑SFT is an 8.03B parameter Llama‑3 model fine‑tuned on the Catalan‑Instruct‑V2 dataset. It was trained on 620 million new tokens and includes 250k additional Catalan instructions. The model is optimized for Catalan language tasks.

Good at

  • Catalan instruction following
  • Information extraction and NER
  • Translation between English and Catalan

Limits

  • No vision support
  • Requires 8 k context length
  • License is llama‑3

Best for

  • Catalan chat applications
  • Catalan RAG pipelines
  • Catalan translation services

Who it’s for. Developers building Catalan‑centric LLM applications or researchers exploring low‑resource language models. The model is suitable for commercial use under the llama‑3 license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.2 GB 4.8 GB
Fits Get file →
IQ3_XS3.5 GB 5.1 GB
Fits Get file →
Q3_K_S3.7 GB 5.2 GB
Fits Get file →
IQ3_S3.7 GB 5.3 GB
Fits Get file →
IQ3_M3.8 GB 5.4 GB
Fits Get file →
Q3_K_M4.0 GB 5.6 GB
Fits Get file →
Q3_K_L4.3 GB 5.9 GB
Fits Get file →
IQ4_XS4.5 GB 6.1 GB
Fits Get file →
Q4_K_S4.7 GB 6.3 GB
Fits Get file →
Q4_K_M4.9 GB 6.5 GB
Fits Get file →
Q5_K_S5.6 GB 7.2 GB
Fits Get file →
Q5_K_M5.7 GB 7.3 GB
Tight Get file →
Q6_K6.6 GB 8.2 GB
Too big Get file →
Q8_08.5 GB 10.1 GB
Too big Get file →
F1616.1 GB 17.6 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_S (file size 4.69 GB, estimated 6.3 GB memory). For 12 GB VRAM, Q5_K_S (5.6 GB, 7.2 GB memory) is a good balance. For 16 GB VRAM, Q6_K (6.6 GB, 8.2 GB memory) provides higher quality.

What GPU do you need for CataLlama-v0.2-Instruct-SFT?

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 Q3_K_L (4.3 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (5.7 GB file, about 7.3 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (16.1 GB file, about 17.6 GB in use).

Which CataLlama-v0.2-Instruct-SFT quant should you choose?

Q4_K_M is the usual starting point for CataLlama-v0.2-Instruct-SFT: it balances file size and quality well. Here it is a 4.9 GB file.

The Q8_0 file is 8.5 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 Q2_K at 3.2 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
Parameters8.03B
Layers32
Trained context8,192 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyCatallama
Licensellama3
Downloads (HF)1,257
Last updated2025-04-01

Frequently asked questions about CataLlama-v0.2-Instruct-SFT

How much VRAM does CataLlama-v0.2-Instruct-SFT need?

About 6.5 GB at Q4_K_M with an 8K context window. That is the 4.9 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 CataLlama-v0.2-Instruct-SFT on an 8 GB GPU?

Yes, with Q5_K_M: the 5.7 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of CataLlama-v0.2-Instruct-SFT GGUF?

It depends on the quant: Q2_K is 3.2 GB, IQ3_XS is 3.5 GB, Q3_K_S is 3.7 GB, IQ3_S is 3.7 GB, IQ3_M is 3.8 GB, Q3_K_M is 4.0 GB and 9 more.

What context length does CataLlama-v0.2-Instruct-SFT support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.1 GB at 8K and 1.1 GB at 8K.

Where can I download CataLlama-v0.2-Instruct-SFT GGUF?

The files are on Hugging Face in the mradermacher/CataLlama-v0.2-Instruct-SFT-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 CataLlama-v0.2-Instruct-SFT use?

Hugging Face lists the license as llama3. 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 CataLlama‑v0.2‑Instruct‑SFT on 8 GB VRAM?

Yes, the Q4_K_S quant uses 4.69 GB file size and requires approximately 6.3 GB VRAM at 8 k context.

Does the model support vision tasks?

No, the model is purely text‑based and has no vision capabilities.

What context length does the model support?

The model was trained with a context length of 8192 tokens.

Other GGUFs of CataLlama-v0.2-Instruct-SFT

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Catallama models

All Catallama →

Other small models

All small models →