FL

FLAMA 0.1 3B

FlamaGGUF by xaviviroUpdated 2024-01-10
Download on Hugging Face
Parameters3.43B
Context2K
Layers26
Architecturellama
Smallest quant2.0 GB
Quick answer

FLAMA 0.1 3B needs about 5.8 GB of memory at Q4_K_M (a 2.6 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 15 quants, from 2.0 GB (Q4_0) to 6.9 GB (F16).

FLAMA 0.1 3B – a 3B Catalan language model in GGUF format

FLAMA 0.1 3B is a 3.43B parameter model fine‑tuned from open_llama_3b_v2 for Catalan. It uses the ChatML prompt template and is available in multiple GGUF quantizations. The model is released under the Apache‑2.0 license.

Good at

  • Catalan language generation
  • ChatML prompt handling
  • Small‑parameter inference

Limits

  • No vision support
  • Context limited to 2048 tokens
  • Requires 5.2–10.1 GB VRAM for 8k context

Best for

  • Local Catalan chatbots
  • Lightweight inference on edge devices
  • Educational language projects

Who it’s for. Developers building Catalan language applications who need a compact model. Researchers wanting to experiment with fine‑tuned 3B models in a permissive license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_02.0 GB 3.2 GB
Fits Get file →
Q2_K2.1 GB 3.3 GB
Fits Get file →
Q3_K_S2.2 GB 3.4 GB
Fits Get file →
Q4_12.2 GB 3.4 GB
Fits Get file →
Q3_K_M2.3 GB 3.5 GB
Fits Get file →
Q3_K_L2.3 GB 3.5 GB
Fits Get file →
Q5_02.4 GB 3.6 GB
Fits Get file →
Q4_K_S2.4 GB 3.6 GB
Fits Get file →
Q4_K_M2.6 GB 3.8 GB
Fits Get file →
Q5_12.6 GB 3.8 GB
Fits Get file →
Q5_K_S2.6 GB 3.8 GB
Fits Get file →
Q5_K_M2.8 GB 3.9 GB
Fits Get file →
Q6_K3.6 GB 4.8 GB
Fits Get file →
Q8_03.6 GB 4.8 GB
Fits Get file →
F166.9 GB 8.0 GB
Too big Get file →

For 8 GB VRAM, Q4_0 (1.98 GB, 5.2 GB memory) or Q2_K (2.15 GB, 5.4 GB memory) are suitable. For 12 GB VRAM, Q4_K_M (2.58 GB, 5.8 GB memory) or Q5_K_M (2.76 GB, 6 GB memory) provide better precision. Estimates are approximate.

What GPU do you need for FLAMA 0.1 3B?

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 Q5_K_M (2.8 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (3.6 GB file, about 6.9 GB in use).
  • 12 GB VRAM: the best quant that fits is F16 (6.9 GB file, about 10.1 GB in use).

Which FLAMA 0.1 3B quant should you choose?

Q4_K_M is the usual starting point for FLAMA 0.1 3B: it balances file size and quality well. Here it is a 2.6 GB file.

The Q8_0 file is 3.6 GB, about 1.4 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 Q4_0 at 2.0 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters3.43B
Layers26
Trained context2,048 tokens
KV cache (fp16)325 KB per token

Source

Quantized byxaviviro
FamilyFlama
Licenseapache-2.0
Downloads (HF)587
Last updated2024-01-10

Frequently asked questions about FLAMA 0.1 3B

How much VRAM does FLAMA 0.1 3B need?

About 5.8 GB at Q4_K_M with an 8K context window. That is the 2.6 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 FLAMA 0.1 3B on an 8 GB GPU?

Yes, with Q6_K: the 3.6 GB file needs about 6.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of FLAMA 0.1 3B GGUF?

It depends on the quant: Q4_0 is 2.0 GB, Q2_K is 2.1 GB, Q3_K_S is 2.2 GB, Q4_1 is 2.2 GB, Q3_K_M is 2.3 GB, Q3_K_L is 2.3 GB and 9 more.

What context length does FLAMA 0.1 3B support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 2.7 GB at 8K and 0.7 GB at 2K.

Where can I download FLAMA 0.1 3B GGUF?

The files are on Hugging Face in the xaviviro/FLAMA-0.1-3B-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 FLAMA 0.1 3B 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 FLAMA 0.1 3B on 8 GB VRAM?

Yes, the Q4_0 quantization uses about 5.2 GB memory at 8k context, fitting within 8 GB VRAM.

Does FLAMA support vision?

No, the model has no vision capabilities.

What license is FLAMA released under?

FLAMA is released under the Apache‑2.0 license.

Similar models

Browse all →

More from xaviviro

All by xaviviro →

More Flama models

All Flama →

Other tiny models

All tiny models →