About

weighted/imatrix quants of https://huggingface.co/OrionStarAI/Orion-14B-Chat-RAG

static quants are available at https://huggingface.co/mradermacher/Orion-14B-Chat-RAG-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 3.5 for the desperate
GGUF i1-IQ1_M 3.7 mostly desperate
GGUF i1-IQ2_XXS 4.2
GGUF i1-IQ2_XS 4.5
GGUF i1-IQ2_S 4.9
GGUF i1-Q2_K_S 5.2 very low quality
GGUF i1-IQ2_M 5.2
GGUF i1-Q2_K 5.6 IQ3_XXS probably better
GGUF i1-IQ3_XXS 5.7 lower quality
GGUF i1-IQ3_XS 6.2
GGUF i1-IQ3_S 6.5 beats Q3_K*
GGUF i1-Q3_K_S 6.5 IQ3_XS probably better
GGUF i1-IQ3_M 6.8
GGUF i1-Q3_K_M 7.2 IQ3_S probably better
GGUF i1-Q3_K_L 7.9 IQ3_M probably better
GGUF i1-IQ4_XS 7.9
GGUF i1-Q4_0_4_4 8.4 fast on arm, low quality
GGUF i1-Q4_0_4_8 8.4 fast on arm+i8mm, low quality
GGUF i1-Q4_0_8_8 8.4 fast on arm+sve, low quality
GGUF i1-Q4_0 8.4 fast, low quality
GGUF i1-Q4_K_S 8.4 optimal size/speed/quality
GGUF i1-Q4_K_M 8.9 fast, recommended
GGUF i1-Q5_K_S 10.1
GGUF i1-Q5_K_M 10.4
GGUF i1-Q6_K 12.0 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
521
GGUF
Model size
14.5B params
Architecture
orion

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/Orion-14B-Chat-RAG-i1-GGUF

Quantized
(3)
this model