About

weighted/imatrix quants of https://huggingface.co./ostorc/Conversational_Spanish_GPT

static quants are available at https://huggingface.co./mradermacher/Conversational_Spanish_GPT-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 i1-IQ1_S 0.2 for the desperate
GGUF i1-IQ1_M 0.2 mostly desperate
GGUF i1-IQ2_XXS 0.2
GGUF i1-IQ2_XS 0.2
GGUF i1-IQ2_S 0.2
GGUF i1-IQ2_M 0.2
GGUF i1-Q2_K_S 0.2 very low quality
GGUF i1-Q2_K 0.2 IQ3_XXS probably better
GGUF i1-IQ3_XXS 0.2 lower quality
GGUF i1-IQ3_XS 0.2
GGUF i1-IQ3_S 0.2 beats Q3_K*
GGUF i1-Q3_K_S 0.2 IQ3_XS probably better
GGUF i1-IQ3_M 0.2
GGUF i1-Q3_K_M 0.2 IQ3_S probably better
GGUF i1-Q3_K_L 0.2 IQ3_M probably better
GGUF i1-IQ4_XS 0.2
GGUF i1-Q4_0 0.2 fast, low quality
GGUF i1-Q4_K_S 0.2 optimal size/speed/quality
GGUF i1-Q4_K_M 0.2 fast, recommended
GGUF i1-Q5_K_S 0.2
GGUF i1-Q5_K_M 0.2
GGUF i1-Q6_K 0.2 practically like static Q6_K

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
269
GGUF
Model size
163M params
Architecture
gpt2

1-bit

2-bit

3-bit

4-bit

5-bit

6-bit

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

Model tree for mradermacher/Conversational_Spanish_GPT-i1-GGUF

Quantized
(2)
this model