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):
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
Model tree for mradermacher/Orion-14B-Chat-RAG-i1-GGUF
Base model
OrionStarAI/Orion-14B-Chat-RAG