base_model: apetersson/DeepSeek-V4-Flash-0731-Abliterated-FP8 language:
- en library_name: transformers license: mit mradermacher: readme_rev: 1 quantized_by: mradermacher tags:
- deepseek-v4
- mixture-of-experts
- abliterated
- fp8
- model-surgery
- mechanistic-interpretability
About
weighted/imatrix quants of https://huggingface.co/apetersson/DeepSeek-V4-Flash-0731-Abliterated-FP8
For a convenient overview and download list, visit our model page for this model.
static quants are available at https://huggingface.co/mradermacher/DeepSeek-V4-Flash-0731-Abliterated-FP8-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 | imatrix | 0.6 | imatrix file (for creating your own quants) |
| PART 1 PART 2 PART 3 | i1-Q2_K | 103.2 | IQ3_XXS probably better |
| PART 1 PART 2 PART 3 | i1-IQ3_S | 122.6 | beats Q3_K* |
| PART 1 PART 2 PART 3 | i1-Q3_K_S | 122.6 | IQ3_XS probably better |
| PART 1 PART 2 PART 3 | i1-IQ3_M | 124.0 | |
| PART 1 PART 2 PART 3 | i1-Q3_K_M | 135.4 | IQ3_S probably better |
| PART 1 PART 2 PART 3 PART 4 | i1-Q3_K_L | 146.5 | IQ3_M probably better |
| PART 1 PART 2 PART 3 PART 4 | i1-IQ4_XS | 151.4 | |
| PART 1 PART 2 PART 3 PART 4 | i1-Q4_0 | 160.9 | fast, low quality |
| PART 1 PART 2 PART 3 PART 4 | i1-Q4_K_S | 161.6 | optimal size/speed/quality |
| PART 1 PART 2 PART 3 PART 4 | i1-Q4_K_M | 171.9 | fast, recommended |
| PART 1 PART 2 PART 3 PART 4 | i1-Q4_1 | 178.0 | |
| P1 P2 P3 P4 P5 | i1-Q5_K_S | 195.7 | |
| P1 P2 P3 P4 P5 | i1-Q5_K_M | 201.7 | |
| P1 P2 P3 P4 P5 | i1-Q6_K | 233.4 | 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.