About

static quants of https://huggingface.co./prithivMLmods/Llama-SmolTalk-3.2-1B-Instruct

weighted/imatrix quants are available at https://huggingface.co./mradermacher/Llama-SmolTalk-3.2-1B-Instruct-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 0.7
GGUF Q3_K_S 0.7
GGUF Q3_K_M 0.8 lower quality
GGUF Q3_K_L 0.8
GGUF IQ4_XS 0.8
GGUF Q4_0_4_4 0.9 fast on arm, low quality
GGUF Q4_K_S 0.9 fast, recommended
GGUF Q4_K_M 0.9 fast, recommended
GGUF Q5_K_S 1.0
GGUF Q5_K_M 1.0
GGUF Q6_K 1.1 very good quality
GGUF Q8_0 1.4 fast, best quality
GGUF f16 2.6 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. Additional thanks to @nicoboss for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.

Downloads last month
986
GGUF
Model size
1.24B params
Architecture
llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for mradermacher/Llama-SmolTalk-3.2-1B-Instruct-GGUF

Dataset used to train mradermacher/Llama-SmolTalk-3.2-1B-Instruct-GGUF