初始化项目，由ModelHub XC社区提供模型
Model: bartowski/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-GGUF Source: Original Platform
This commit is contained in:
ModelHub XC
61
.gitattributes
vendored
Normal file
61
.gitattributes
vendored
Normal file
@@ -0,0 +1,61 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-bf16.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0.imatrix filter=lfs diff=lfs merge=lfs -text
|
||||
183
README.md
Normal file
183
README.md
Normal file
@@ -0,0 +1,183 @@
|
||||
---
|
||||
quantized_by: bartowski
|
||||
pipeline_tag: text-generation
|
||||
language:
|
||||
- en
|
||||
base_model_relation: quantized
|
||||
tags:
|
||||
- nsfw
|
||||
- explicit
|
||||
- roleplay
|
||||
- unaligned
|
||||
- dangerous
|
||||
- ERP
|
||||
license: gemma
|
||||
base_model: ReadyArt/The-Omega-Abomination-Gemma3-12B-v1.0
|
||||
---
|
||||
|
||||
## Llamacpp imatrix Quantizations of The-Omega-Abomination-Gemma3-12B-v1.0 by ReadyArt
|
||||
|
||||
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b5074">b5074</a> for quantization.
|
||||
|
||||
Original model: https://huggingface.co/ReadyArt/The-Omega-Abomination-Gemma3-12B-v1.0
|
||||
|
||||
All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)
|
||||
|
||||
Run them in [LM Studio](https://lmstudio.ai/)
|
||||
|
||||
Run them directly with [llama.cpp](https://github.com/ggerganov/llama.cpp), or any other llama.cpp based project
|
||||
|
||||
## Prompt format
|
||||
|
||||
```
|
||||
<bos><start_of_turn>user
|
||||
{system_prompt}
|
||||
|
||||
{prompt}<end_of_turn>
|
||||
<start_of_turn>model
|
||||
<end_of_turn>
|
||||
<start_of_turn>model
|
||||
```
|
||||
|
||||
## Download a file (not the whole branch) from below:
|
||||
|
||||
| Filename | Quant type | File Size | Split | Description |
|
||||
| -------- | ---------- | --------- | ----- | ----------- |
|
||||
| [The-Omega-Abomination-Gemma3-12B-v1.0-bf16.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-bf16.gguf) | bf16 | 23.54GB | false | Full BF16 weights. |
|
||||
| [The-Omega-Abomination-Gemma3-12B-v1.0-Q8_0.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q8_0.gguf) | Q8_0 | 12.51GB | false | Extremely high quality, generally unneeded but max available quant. |
|
||||
| [The-Omega-Abomination-Gemma3-12B-v1.0-Q6_K_L.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q6_K_L.gguf) | Q6_K_L | 9.90GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
|
||||
| [The-Omega-Abomination-Gemma3-12B-v1.0-Q6_K.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q6_K.gguf) | Q6_K | 9.66GB | false | Very high quality, near perfect, *recommended*. |
|
||||
| [The-Omega-Abomination-Gemma3-12B-v1.0-Q5_K_L.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q5_K_L.gguf) | Q5_K_L | 8.69GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
|
||||
| [The-Omega-Abomination-Gemma3-12B-v1.0-Q5_K_M.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q5_K_M.gguf) | Q5_K_M | 8.44GB | false | High quality, *recommended*. |
|
||||
| [The-Omega-Abomination-Gemma3-12B-v1.0-Q5_K_S.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q5_K_S.gguf) | Q5_K_S | 8.23GB | false | High quality, *recommended*. |
|
||||
| [The-Omega-Abomination-Gemma3-12B-v1.0-Q4_1.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q4_1.gguf) | Q4_1 | 7.56GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
|
||||
| [The-Omega-Abomination-Gemma3-12B-v1.0-Q4_K_L.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q4_K_L.gguf) | Q4_K_L | 7.54GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
|
||||
| [The-Omega-Abomination-Gemma3-12B-v1.0-Q4_K_M.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q4_K_M.gguf) | Q4_K_M | 7.30GB | false | Good quality, default size for most use cases, *recommended*. |
|
||||
| [The-Omega-Abomination-Gemma3-12B-v1.0-Q4_K_S.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q4_K_S.gguf) | Q4_K_S | 6.94GB | false | Slightly lower quality with more space savings, *recommended*. |
|
||||
| [The-Omega-Abomination-Gemma3-12B-v1.0-Q4_0.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q4_0.gguf) | Q4_0 | 6.91GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
|
||||
| [The-Omega-Abomination-Gemma3-12B-v1.0-IQ4_NL.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-IQ4_NL.gguf) | IQ4_NL | 6.89GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
|
||||
| [The-Omega-Abomination-Gemma3-12B-v1.0-Q3_K_XL.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q3_K_XL.gguf) | Q3_K_XL | 6.72GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
|
||||
| [The-Omega-Abomination-Gemma3-12B-v1.0-IQ4_XS.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-IQ4_XS.gguf) | IQ4_XS | 6.55GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
|
||||
| [The-Omega-Abomination-Gemma3-12B-v1.0-Q3_K_L.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q3_K_L.gguf) | Q3_K_L | 6.48GB | false | Lower quality but usable, good for low RAM availability. |
|
||||
| [The-Omega-Abomination-Gemma3-12B-v1.0-Q3_K_M.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q3_K_M.gguf) | Q3_K_M | 6.01GB | false | Low quality. |
|
||||
| [The-Omega-Abomination-Gemma3-12B-v1.0-IQ3_M.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-IQ3_M.gguf) | IQ3_M | 5.66GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
|
||||
| [The-Omega-Abomination-Gemma3-12B-v1.0-Q3_K_S.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q3_K_S.gguf) | Q3_K_S | 5.46GB | false | Low quality, not recommended. |
|
||||
| [The-Omega-Abomination-Gemma3-12B-v1.0-IQ3_XS.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-IQ3_XS.gguf) | IQ3_XS | 5.21GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
|
||||
| [The-Omega-Abomination-Gemma3-12B-v1.0-Q2_K_L.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q2_K_L.gguf) | Q2_K_L | 5.01GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
|
||||
| [The-Omega-Abomination-Gemma3-12B-v1.0-IQ3_XXS.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-IQ3_XXS.gguf) | IQ3_XXS | 4.78GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
|
||||
| [The-Omega-Abomination-Gemma3-12B-v1.0-Q2_K.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q2_K.gguf) | Q2_K | 4.77GB | false | Very low quality but surprisingly usable. |
|
||||
| [The-Omega-Abomination-Gemma3-12B-v1.0-IQ2_M.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-IQ2_M.gguf) | IQ2_M | 4.31GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
|
||||
| [The-Omega-Abomination-Gemma3-12B-v1.0-IQ2_S.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-IQ2_S.gguf) | IQ2_S | 4.02GB | false | Low quality, uses SOTA techniques to be usable. |
|
||||
|
||||
## Embed/output weights
|
||||
|
||||
Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.
|
||||
|
||||
## Downloading using huggingface-cli
|
||||
|
||||
<details>
|
||||
<summary>Click to view download instructions</summary>
|
||||
|
||||
First, make sure you have hugginface-cli installed:
|
||||
|
||||
```
|
||||
pip install -U "huggingface_hub[cli]"
|
||||
```
|
||||
|
||||
Then, you can target the specific file you want:
|
||||
|
||||
```
|
||||
huggingface-cli download bartowski/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-GGUF --include "ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q4_K_M.gguf" --local-dir ./
|
||||
```
|
||||
|
||||
If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:
|
||||
|
||||
```
|
||||
huggingface-cli download bartowski/ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-GGUF --include "ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q8_0/*" --local-dir ./
|
||||
```
|
||||
|
||||
You can either specify a new local-dir (ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q8_0) or download them all in place (./)
|
||||
|
||||
</details>
|
||||
|
||||
## ARM/AVX information
|
||||
|
||||
Previously, you would download Q4_0_4_4/4_8/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass.
|
||||
|
||||
Now, however, there is something called "online repacking" for weights. details in [this PR](https://github.com/ggerganov/llama.cpp/pull/9921). If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly.
|
||||
|
||||
As of llama.cpp build [b4282](https://github.com/ggerganov/llama.cpp/releases/tag/b4282) you will not be able to run the Q4_0_X_X files and will instead need to use Q4_0.
|
||||
|
||||
Additionally, if you want to get slightly better quality for , you can use IQ4_NL thanks to [this PR](https://github.com/ggerganov/llama.cpp/pull/10541) which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed incrase.
|
||||
|
||||
<details>
|
||||
<summary>Click to view Q4_0_X_X information (deprecated</summary>
|
||||
|
||||
I'm keeping this section to show the potential theoretical uplift in performance from using the Q4_0 with online repacking.
|
||||
|
||||
<details>
|
||||
<summary>Click to view benchmarks on an AVX2 system (EPYC7702)</summary>
|
||||
|
||||
| model | size | params | backend | threads | test | t/s | % (vs Q4_0) |
|
||||
| ------------------------------ | ---------: | ---------: | ---------- | ------: | ------------: | -------------------: |-------------: |
|
||||
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp512 | 204.03 ± 1.03 | 100% |
|
||||
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp1024 | 282.92 ± 0.19 | 100% |
|
||||
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp2048 | 259.49 ± 0.44 | 100% |
|
||||
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg128 | 39.12 ± 0.27 | 100% |
|
||||
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg256 | 39.31 ± 0.69 | 100% |
|
||||
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg512 | 40.52 ± 0.03 | 100% |
|
||||
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp512 | 301.02 ± 1.74 | 147% |
|
||||
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp1024 | 287.23 ± 0.20 | 101% |
|
||||
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp2048 | 262.77 ± 1.81 | 101% |
|
||||
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg128 | 18.80 ± 0.99 | 48% |
|
||||
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg256 | 24.46 ± 3.04 | 83% |
|
||||
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg512 | 36.32 ± 3.59 | 90% |
|
||||
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp512 | 271.71 ± 3.53 | 133% |
|
||||
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp1024 | 279.86 ± 45.63 | 100% |
|
||||
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp2048 | 320.77 ± 5.00 | 124% |
|
||||
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg128 | 43.51 ± 0.05 | 111% |
|
||||
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg256 | 43.35 ± 0.09 | 110% |
|
||||
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg512 | 42.60 ± 0.31 | 105% |
|
||||
|
||||
Q4_0_8_8 offers a nice bump to prompt processing and a small bump to text generation
|
||||
|
||||
</details>
|
||||
|
||||
</details>
|
||||
|
||||
## Which file should I choose?
|
||||
|
||||
<details>
|
||||
<summary>Click here for details</summary>
|
||||
|
||||
A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9)
|
||||
|
||||
The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.
|
||||
|
||||
If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.
|
||||
|
||||
If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.
|
||||
|
||||
Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.
|
||||
|
||||
If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.
|
||||
|
||||
If you want to get more into the weeds, you can check out this extremely useful feature chart:
|
||||
|
||||
[llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix)
|
||||
|
||||
But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.
|
||||
|
||||
These I-quants can also be used on CPU, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
|
||||
|
||||
</details>
|
||||
|
||||
## Credits
|
||||
|
||||
Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset.
|
||||
|
||||
Thank you ZeroWw for the inspiration to experiment with embed/output.
|
||||
|
||||
Thank you to LM Studio for sponsoring my work.
|
||||
|
||||
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a3ac36cf664677c2cf8c12272bb44fc8577fc10f5146106ecb5e8ed9fa636f26
|
||||
size 4310293440
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e557f196b7f228fe3439a74a84e1831720c61bfe3028b1dcb0c05a3c4ad6c630
|
||||
size 4020542400
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1349e7eb1a720de9e51c21612621565868b917029f99768a712b980cf676a1ab
|
||||
size 5655522752
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8d0ba70e792ae5271df0e2f43e21a655317126b0e9bf676512df3c67f3412ee9
|
||||
size 5205966272
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3a0e4377217bc0f52420b19b2acd17a628cb341b834f3c50509c708e5ffe5a9f
|
||||
size 4784733120
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9cc711cb8bbdab2e2ddd9b50e0f4072b27012e800bc11e0e033ece70b9adaa45
|
||||
size 6886964672
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:46ba00f580206cc39cf955930353a2778bf8cc57d98cbf179aca8c2d4be42b3e
|
||||
size 6550764992
|
||||
3
ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q2_K.gguf
Normal file
3
ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q2_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f7d110766acc2f9f81e9b673dd5c6746755238b53cbdd0f078e457241530fb07
|
||||
size 4768021952
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e212c2e16ec35cfb8e3b0137d704e25958a04717474f205e637e7e92e4884679
|
||||
size 5011816800
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:89417358c11d9d50371985c312b0bfcead11874f592ea7ec8c0f7e57b3a004f3
|
||||
size 6479986112
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:32309947647b195b4e45ebfebca381fb598f1c927903eacc24098cae3e0c54bf
|
||||
size 6008618432
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2e913cbf53ce9b4e7a3d5e0b4880fcd8d824915480d051d7bb9dcaec4b2d47b5
|
||||
size 5458116032
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2e44c8606c03f6c0664ccab822c813212df457bc658c23e7d32bd1d505cce1b0
|
||||
size 6723780960
|
||||
3
ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q4_0.gguf
Normal file
3
ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q4_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f1d718c6c752d6086fc8448239a7bba69423d92e4eac3d5625b41c379ee39e0c
|
||||
size 6909083072
|
||||
3
ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q4_1.gguf
Normal file
3
ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q4_1.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2d8deb707a2fe3ccbe24cbe3a35d2db5f3cb0c83acfad983f7a8db660abff0b6
|
||||
size 7559364032
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:765437972a78eec8166c20e764ac4114ac6b41c66bd9e5f99af00697f4c1fece
|
||||
size 7544373600
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:66bc9fe47325351a2bbc910198bcca98c29679d5d15f2846ba5c2cbcafd8b67d
|
||||
size 7300578752
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f5e4d2c1393f3b08726c5e4dbb1bfe3c29250ac8abd15f92043d9756f7427fbd
|
||||
size 6935133632
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b9dc5cf97606ec90b67a1e91cc288aaea2f8d52691e80d04f60f1a9d782fde93
|
||||
size 8688632160
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:95bfb9ce543a99040d6fbd81625ed7e8f4ecd74350495c66605b464299de9790
|
||||
size 8444837312
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b15dfb35a0d206f1d5b1443d74c34bda44bda073c34cc01bd470793d151d3b8e
|
||||
size 8231763392
|
||||
3
ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q6_K.gguf
Normal file
3
ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q6_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5850b0d6bcfa5e1d7f1c0753dd116aa37ed63d0515380a1536ad3ba36d97c855
|
||||
size 9660612032
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:853b5e0c62a538173c58e9c28d6ee1066d07589f06965b0cbfda2eae6bc6a28e
|
||||
size 9904406880
|
||||
3
ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q8_0.gguf
Normal file
3
ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-Q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fdb7c0ad04cc8afa621807195c0172b3c99461d5b424cb21402e9f9f698c761a
|
||||
size 12509954400
|
||||
3
ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-bf16.gguf
Normal file
3
ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0-bf16.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2da745588aacc4512c1711385bdf799a40b929d837ddf784dd5ef19ceca40bf5
|
||||
size 23539666464
|
||||
3
ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0.imatrix
Normal file
3
ReadyArt_The-Omega-Abomination-Gemma3-12B-v1.0.imatrix
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:678fb1d791b0a8bea451bf6caf2f04fcf1baf52badd3dc03ec8c38a87c22cb4d
|
||||
size 7433114
|
||||
Reference in New Issue
Block a user