FI

fietje 2

FietjeGGUF by BramVanroyUpdated 2024-08-27
Download on Hugging Face
Parameters2.78B
Context2K
Layers32
Architecturephi2
Smallest quant1.4 GB
Quick answer

fietje 2 needs about 4.9 GB of memory at Q4_K_M (a 1.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 6 quants, from 1.4 GB (Q3_K_M) to 5.6 GB (F16).

fietje 2 – a 2.78B phi2 model in GGUF format

fietje 2 is a 2.78B parameter phi2 model released under the MIT license. It supports a 2048 token context window and is available in several quantized forms for efficient deployment.

Good at

  • Fast inference on modest GPUs
  • Low memory footprint
  • Good general language understanding

Limits

  • No vision or multimodal support
  • Limited to 2048 token context
  • Requires llama.cpp for quantized use

Best for

  • Chatbots on edge devices
  • Rapid prototyping of language models
  • Educational demonstrations of phi2 architecture

Who it’s for. Developers and researchers who need a small, open‑source language model that can run on consumer hardware. The model is suitable for projects that require quick iteration and low resource consumption.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M1.4 GB 2.6 GB
Fits Get file →
Q4_K_M1.7 GB 2.9 GB
Fits Get file →
Q5_K_M2.0 GB 3.2 GB
Fits Get file →
Q6_K2.3 GB 3.5 GB
Fits Get file →
Q8_03.0 GB 4.1 GB
Fits Get file →
F165.6 GB 6.7 GB
Fits Get file →

For 8 GB VRAM, Q3_K_M (1.43 GB file, 4.6 GB memory at 8 k context) is recommended. If more VRAM is available, Q4_K_M (1.74 GB, 4.9 GB memory) or Q5_K_M (2 GB, 5.2 GB memory) provide better quality. The full F16 (5.56 GB, 8.7 GB memory) offers the highest fidelity but needs more resources.

What GPU do you need for fietje 2?

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 Q6_K (2.3 GB file, about 5.5 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (3.0 GB file, about 6.1 GB in use).
  • 12 GB VRAM: the best quant that fits is F16 (5.6 GB file, about 8.7 GB in use).

Which fietje 2 quant should you choose?

Q4_K_M is the usual starting point for fietje 2: it balances file size and quality well. Here it is a 1.7 GB file.

The Q8_0 file is 3.0 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 Q3_K_M at 1.4 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturephi2
Parameters2.78B
Layers32
Trained context2,048 tokens
KV cache (fp16)320 KB per token

Source

Quantized byBramVanroy
FamilyFietje
Licensemit
Downloads (HF)1,286
Last updated2024-08-27

Frequently asked questions about fietje 2

How much VRAM does fietje 2 need?

About 4.9 GB at Q4_K_M with an 8K context window. That is the 1.7 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 fietje 2 on an 8 GB GPU?

Yes, with Q8_0: the 3.0 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 fietje 2 GGUF?

It depends on the quant: Q3_K_M is 1.4 GB, Q4_K_M is 1.7 GB, Q5_K_M is 2.0 GB, Q6_K is 2.3 GB, Q8_0 is 3.0 GB, F16 is 5.6 GB.

What context length does fietje 2 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 fietje 2 GGUF?

The files are on Hugging Face in the BramVanroy/fietje-2-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 fietje 2 use?

Hugging Face lists the license as mit. 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 fietje 2 on 8 GB VRAM?

Yes, the Q3_K_M quantization uses about 4.6 GB of VRAM at 8 k context, fitting comfortably in 8 GB.

Does fietje 2 support vision tasks?

No, the model is purely text‑based and does not include vision capabilities.

Similar models

Browse all →

More from BramVanroy

All by BramVanroy →

More Fietje models

All Fietje →

Other tiny models

All tiny models →