About

weighted/imatrix quants of https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct

static quants are available at https://huggingface.co/mradermacher/Llama-4-Maverick-17B-128E-Instruct-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
PART 1 PART 2 i1-IQ1_S 80.7 for the desperate
PART 1 PART 2 i1-IQ1_M 89.8 mostly desperate
PART 1 PART 2 PART 3 i1-IQ2_XXS 104.8
PART 1 PART 2 PART 3 i1-IQ2_XS 117.0
PART 1 PART 2 PART 3 i1-IQ2_S 118.4
PART 1 PART 2 PART 3 i1-IQ2_M 130.4
PART 1 PART 2 PART 3 i1-Q2_K_S 136.1 very low quality
PART 1 PART 2 PART 3 i1-Q2_K 145.7 IQ3_XXS probably better
PART 1 PART 2 PART 3 PART 4 i1-IQ3_XXS 153.9 lower quality
PART 1 PART 2 PART 3 PART 4 i1-IQ3_XS 163.4
PART 1 PART 2 PART 3 PART 4 i1-Q3_K_S 172.8 IQ3_XS probably better
PART 1 PART 2 PART 3 PART 4 i1-IQ3_S 172.8 beats Q3_K*
PART 1 PART 2 PART 3 PART 4 i1-IQ3_M 175.1
PART 1 PART 2 PART 3 PART 4 i1-Q3_K_M 191.2 IQ3_S probably better
P1 P2 P3 P4 P5 i1-Q3_K_L 207.1 IQ3_M probably better
P1 P2 P3 P4 P5 i1-IQ4_XS 213.4
P1 P2 P3 P4 P5 i1-Q4_0 226.9 fast, low quality
P1 P2 P3 P4 P5 i1-Q4_K_S 227.9 optimal size/speed/quality
P1 P2 P3 P4 P5 i1-Q4_K_M 242.9 fast, recommended
P1 P2 P3 P4 P5 P6 i1-Q4_1 250.8
P1 P2 P3 P4 P5 P6 i1-Q5_K_S 275.8
P1 P2 P3 P4 P5 P6 i1-Q5_K_M 284.6
P1 P2 P3 P4 P5 P6 P7 i1-Q6_K 328.9 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

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for mradermacher/Llama-4-Maverick-17B-128E-Instruct-i1-GGUF