mradermacher/Qwen2-VL-2B-Instruct-abliterated-i1-GGUF

About

weighted/imatrix quants of https://huggingface.co/huihui-ai/Qwen2-VL-2B-Instruct-abliterated

For a convenient overview and download list, visit our model page for this model.

static quants are available at https://huggingface.co/mradermacher/Qwen2-VL-2B-Instruct-abliterated-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	0.6	for the desperate
GGUF	i1-IQ1_M	0.6	mostly desperate
GGUF	i1-IQ2_XXS	0.7
GGUF	i1-IQ2_XS	0.7
GGUF	i1-IQ2_S	0.8
GGUF	i1-IQ2_M	0.8
GGUF	i1-Q2_K_S	0.8	very low quality
GGUF	i1-Q2_K	0.9	IQ3_XXS probably better
GGUF	i1-IQ3_XXS	0.9	lower quality
GGUF	i1-IQ3_XS	0.9
GGUF	i1-Q3_K_S	1.0	IQ3_XS probably better
GGUF	i1-IQ3_S	1.0	beats Q3_K*
GGUF	i1-IQ3_M	1.0
GGUF	i1-Q3_K_M	1.0	IQ3_S probably better
GGUF	i1-Q3_K_L	1.1	IQ3_M probably better
GGUF	i1-IQ4_XS	1.1
GGUF	i1-Q4_0	1.2	fast, low quality
GGUF	i1-Q4_K_S	1.2	optimal size/speed/quality
GGUF	i1-Q4_K_M	1.2	fast, recommended
GGUF	i1-Q5_K_S	1.4
GGUF	i1-Q5_K_M	1.4
GGUF	i1-Q6_K	1.6	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