SAVRN
Search Contact SAVRN

Open-weight model

AmberSafe-i1-GGUF

by Team Mradermacher mradermacher/AmberSafe-i1-GGUF

weighted/imatrix quants of https://huggingface.co/IFM/AmberSafe For a convenient overview and download list, visit our model page for this model.

Parameters
Context
Weights77.3 GB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads982

Model Card

By Team Mradermacher, published under apache-2.0, revision 4fe6e6c844be.

weighted/imatrix quants of https://huggingface.co/IFM/AmberSafe For a convenient overview and download list, visit our model page for this model. static quants are available at https://huggingface.co/mradermacher/AmberSafe-GGUF 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. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality quant And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 See…

Read Team Mradermacher's full model card

About

weighted/imatrix quants of https://huggingface.co/IFM/AmberSafe

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

static quants are available at https://huggingface.co/mradermacher/AmberSafe-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 1.6 for the desperate
GGUF i1-IQ1_M 1.8 mostly desperate
GGUF i1-IQ2_XXS 2.0
GGUF i1-IQ2_XS 2.1
GGUF i1-IQ2_S 2.3
GGUF i1-IQ2_M 2.5
GGUF i1-Q2_K 2.6 IQ3_XXS probably better
GGUF i1-IQ3_XXS 2.7 lower quality
GGUF i1-IQ3_XS 2.9
GGUF i1-IQ3_S 3.0 beats Q3_K*
GGUF i1-Q3_K_S 3.0 IQ3_XS probably better
GGUF i1-IQ3_M 3.2
GGUF i1-Q3_K_M 3.4 IQ3_S probably better
GGUF i1-Q3_K_L 3.7 IQ3_M probably better
GGUF i1-IQ4_XS 3.7
GGUF i1-Q4_0_4_4 3.9 fast on arm, low quality
GGUF i1-Q4_0_4_8 3.9 fast on arm+i8mm, low quality
GGUF i1-Q4_0_8_8 3.9 fast on arm+sve, low quality
GGUF i1-Q4_0 3.9 fast, low quality
GGUF i1-Q4_K_S 4.0 optimal size/speed/quality
GGUF i1-Q4_K_M 4.2 fast, recommended
GGUF i1-Q5_K_S 4.8
GGUF i1-Q5_K_M 4.9
GGUF i1-Q6_K 5.6 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

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.

Identity and Version

Repository
mradermacher/AmberSafe-i1-GGUF
Publisher
Team Mradermacher
Task
Not stated by the source
Modality
Other
Library
transformers
Parameters
Not stated by the source
Languages
en
Revision
4fe6e6c844be8d529df7d1e87762faf04ea64b01
First published
2024-10-05
Last updated
2026-09-18

Files and Weights

27 files, 77.3 GB in total. The weights are 24 files totalling 77.3 GB in gguf.

Weights24 files · 77.3 GB
Documentation1 file · 5.3 KB
Other1 file · 4.6 MB
Repository1 file · 3.0 KB
Every file
FileTypeSizeSHA-256
AmberSafe.i1-IQ1_M.ggufWeights1.7 GB 5675c6ed8544
AmberSafe.i1-IQ1_S.ggufWeights1.5 GB d7326b960c3a
AmberSafe.i1-IQ2_M.ggufWeights2.4 GB 5bcc23aa582e
AmberSafe.i1-IQ2_S.ggufWeights2.2 GB 63af99c41ece
AmberSafe.i1-IQ2_XS.ggufWeights2.0 GB 9e5d0cc263a0
AmberSafe.i1-IQ2_XXS.ggufWeights1.9 GB f1134818c50c
AmberSafe.i1-IQ3_M.ggufWeights3.1 GB cb2f783809f4
AmberSafe.i1-IQ3_S.ggufWeights2.9 GB 4b367c013801
AmberSafe.i1-IQ3_XS.ggufWeights2.8 GB 2012da88eade
AmberSafe.i1-IQ3_XXS.ggufWeights2.6 GB d7d5066f86b0
AmberSafe.i1-IQ4_XS.ggufWeights3.6 GB 0dd0eeac6681
AmberSafe.i1-Q2_K.ggufWeights2.5 GB df53830975ca
AmberSafe.i1-Q3_K_L.ggufWeights3.6 GB a75c49ac20b3
AmberSafe.i1-Q3_K_M.ggufWeights3.3 GB e4fe7e91488e
AmberSafe.i1-Q3_K_S.ggufWeights2.9 GB 8865355f61e2
AmberSafe.i1-Q4_0.ggufWeights3.8 GB c393072b8f68
AmberSafe.i1-Q4_0_4_4.ggufWeights3.8 GB 42aac257a8c7
AmberSafe.i1-Q4_0_4_8.ggufWeights3.8 GB feda557ba624
AmberSafe.i1-Q4_0_8_8.ggufWeights3.8 GB 6eb020f02975
AmberSafe.i1-Q4_K_M.ggufWeights4.1 GB badc76a07c46
AmberSafe.i1-Q4_K_S.ggufWeights3.9 GB 05c237a37e99
AmberSafe.i1-Q5_K_M.ggufWeights4.8 GB 6bcfe7c5321c
AmberSafe.i1-Q5_K_S.ggufWeights4.7 GB 4e254df88da1
AmberSafe.i1-Q6_K.ggufWeights5.5 GB b0c0775eec59
README.mdDocumentation5.3 KB
imatrix.datOther4.6 MB b216b7fdfa43
.gitattributesRepository3.0 KB

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
77.3 GB
Download from Team Mradermacher

Released by Team Mradermacher through its official repository on Hugging Face. Read the license.

Built From

  • Derived from IFM/AmberSafe
  • Quantized from IFM/AmberSafe
  • Trained on (disclosed) PKU-Alignment/PKU-SafeRLHF

Memory Requirements

PrecisionWeights in memory
As published77.3 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About AmberSafe-i1-GGUF

Can I use AmberSafe-i1-GGUF commercially?

Yes. AmberSafe-i1-GGUF is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.