mradermacher/Q25-1.5B-VeoLu-GGUF

---

base_model: Alfitaria/Q25-1.5B-VeoLu datasets:

• allura-org/fujin-cleaned-stage-1
• Dampfinchen/CreativeWritingMultiturn
• ToastyPigeon/SpringDragon
• allura-org/medquadsharegpt
• allura-org/scienceqasharegpt
• Alignment-Lab-AI/orcamath-sharegpt

language:

• en

library_name: transformers quantized_by: mradermacher tags:

• mergekit
• merge
• llama-factory
• lora

---

About

static quants of https://huggingface.co/Alfitaria/Q25-1.5B-VeoLu

weighted/imatrix quants are available at https://huggingface.co/mradermacher/Q25-1.5B-VeoLu-i1-GGUF

Usage

If you are unsure how to use GGUF files, refer to one of TheBloke's
READMEs for
more details, including on how to concatenate multi-part files.

Provided Quants

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Link	Type	Size/GB	Notes
GGUF	Q2_K	0.9
GGUF	Q3K_S	1.0
GGUF	Q3K_M	1.0	lower quality
GGUF	Q3K_L	1.1
GGUF	IQ4_XS	1.1
GGUF	Q404_4	1.2	fast on arm, low quality
GGUF	Q4K_S	1.2	fast, recommended
GGUF	Q4K_M	1.2	fast, recommended
GGUF	Q5K_S	1.4
GGUF	Q5K_M	1.4
GGUF	Q6_K	1.6	very good quality
GGUF	Q8_0	2.0	fast, best quality
GGUF	f16	3.7	16 bpw, overkill

Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):

!image.png

And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9

FAQ / Model Request

See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.

Thanks

I thank my company, nethype GmbH, for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.