base_model: AEON-7/Gemma-4-12B-it-AEON-Abliterated-K4-BF16
language:
- en
library_name: transformers
license: gemma
model_type: gemma4_unified
mradermacher:
readme_rev: 1
quantized_by: mradermacher
tags: - 12b
- aarch64
- abliterated
- aeon
- aeon-7
- agentic
- arm64
- bf16
- bfloat16
- biprojection
- blackwell
- capability-preserving
- chat
- chunked-prefill
- coding
- conversational
- dense
- dgx-spark
- english
- function-calling
- gb10
- gemma
- gemma-4
- gemma-4-12B
- gemma4
- gemma4_unified
- gpu
- grace-blackwell
- heretic
- instruct
- k4-biprojection
- long-context
- low-drift
- multi-direction-biprojection
- multimodal
- multimodal-capable
- nvidia
- openai-api
- openai-compatible
- prefix-caching
- production-ready
- reasoning
- refusal-removed
- safetensors
- sm_121a
- text-generation
- thinking
- tool-calling
- transformer
- transformers
- trevor-js
- uncensored
- unfiltered
- vision
- vision-language
- vllm
About
weighted/imatrix quants of https://huggingface.co/AEON-7/Gemma-4-12B-it-AEON-Abliterated-K4-BF16
For a convenient overview and download list, visit our model page for this model.
static quants are available at https://huggingface.co/mradermacher/Gemma-4-12B-it-AEON-Abliterated-K4-BF16-GGUF
This is a vision model - mmproj files (if any) will be in the static repository.
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 | imatrix | 0.1 | imatrix file (for creating your own quants) |
| GGUF | i1-IQ1_S | 3.1 | for the desperate |
| GGUF | i1-IQ1_M | 3.3 | mostly desperate |
| GGUF | i1-IQ2_XXS | 3.7 | |
| GGUF | i1-IQ2_XS | 4.0 | |
| GGUF | i1-IQ2_S | 4.2 | |
| GGUF | i1-IQ2_M | 4.5 | |
| GGUF | i1-Q2_K_S | 4.6 | very low quality |
| GGUF | i1-Q2_K | 4.9 | IQ3_XXS probably better |
| GGUF | i1-IQ3_XXS | 4.9 | lower quality |
| GGUF | i1-IQ3_XS | 5.4 | |
| GGUF | i1-IQ3_S | 5.6 | beats Q3_K* |
| GGUF | i1-Q3_K_S | 5.6 | IQ3_XS probably better |
| GGUF | i1-IQ3_M | 5.8 | |
| GGUF | i1-Q3_K_M | 6.2 | IQ3_S probably better |
| GGUF | i1-Q3_K_L | 6.7 | IQ3_M probably better |
| GGUF | i1-IQ4_XS | 6.7 | |
| GGUF | i1-IQ4_NL | 7.1 | prefer IQ4_XS |
| GGUF | i1-Q4_0 | 7.1 | fast, low quality |
| GGUF | i1-Q4_K_S | 7.1 | optimal size/speed/quality |
| GGUF | i1-Q4_K_M | 7.5 | fast, recommended |
| GGUF | i1-Q4_1 | 7.8 | |
| GGUF | i1-Q5_K_S | 8.4 | |
| GGUF | i1-Q5_K_M | 8.6 | |
| GGUF | i1-Q6_K | 9.9 | 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.