mradermacher/Llama3-ChatQA-1.5-70B-i1-GGUF

About

weighted/imatrix quants of https://huggingface.co/nvidia/Llama3-ChatQA-1.5-70B

static quants are available at https://huggingface.co/mradermacher/Llama3-ChatQA-1.5-70B-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	15.4	for the desperate
GGUF	i1-IQ1_M	16.9	mostly desperate
GGUF	i1-IQ2_XXS	19.2
GGUF	i1-IQ2_XS	21.2
GGUF	i1-IQ2_S	22.3
GGUF	i1-IQ2_M	24.2
GGUF	i1-Q2_K	26.5	IQ3_XXS probably better
GGUF	i1-IQ3_XXS	27.6	lower quality
GGUF	i1-IQ3_XS	29.4
GGUF	i1-IQ3_S	31.0	beats Q3_K*
GGUF	i1-Q3_K_S	31.0	IQ3_XS probably better
GGUF	i1-IQ3_M	32.0
GGUF	i1-Q3_K_M	34.4	IQ3_S probably better
GGUF	i1-Q3_K_L	37.2	IQ3_M probably better
GGUF	i1-IQ4_XS	38.0
GGUF	i1-Q4_0	40.2	fast, low quality
GGUF	i1-Q4_K_S	40.4	optimal size/speed/quality
GGUF	i1-Q4_K_M	42.6	fast, recommended
GGUF	i1-Q5_K_S	48.8
GGUF	i1-Q5_K_M	50.0
PART 1 PART 2	i1-Q6_K	58.0	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.