初始化项目，由ModelHub XC社区提供模型

Model: bartowski/TheDrummer_Cydonia-R1-24B-v4.1-GGUF
Source: Original Platform

.gitattributes

@@ -0,0 +1,75 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 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
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack 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
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* 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
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+ 
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+
+TheDrummer_Cydonia-R1-24B-v4.1-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+TheDrummer_Cydonia-R1-24B-v4.1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+TheDrummer_Cydonia-R1-24B-v4.1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+TheDrummer_Cydonia-R1-24B-v4.1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+TheDrummer_Cydonia-R1-24B-v4.1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
+TheDrummer_Cydonia-R1-24B-v4.1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+TheDrummer_Cydonia-R1-24B-v4.1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
+TheDrummer_Cydonia-R1-24B-v4.1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
+TheDrummer_Cydonia-R1-24B-v4.1-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+TheDrummer_Cydonia-R1-24B-v4.1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+TheDrummer_Cydonia-R1-24B-v4.1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+TheDrummer_Cydonia-R1-24B-v4.1-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
+TheDrummer_Cydonia-R1-24B-v4.1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+TheDrummer_Cydonia-R1-24B-v4.1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
+TheDrummer_Cydonia-R1-24B-v4.1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
+TheDrummer_Cydonia-R1-24B-v4.1-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+TheDrummer_Cydonia-R1-24B-v4.1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+TheDrummer_Cydonia-R1-24B-v4.1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+TheDrummer_Cydonia-R1-24B-v4.1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
+TheDrummer_Cydonia-R1-24B-v4.1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+TheDrummer_Cydonia-R1-24B-v4.1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+
+TheDrummer_Cydonia-R1-24B-v4.1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+TheDrummer_Cydonia-R1-24B-v4.1-imatrix.gguf filter=lfs diff=lfs merge=lfs -text
+TheDrummer_Cydonia-R1-24B-v4.1-bf16.gguf filter=lfs diff=lfs merge=lfs -text
+TheDrummer_Cydonia-R1-24B-v4.1-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+TheDrummer_Cydonia-R1-24B-v4.1-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,166 @@
+---
+quantized_by: bartowski
+pipeline_tag: text-generation
+base_model: TheDrummer/Cydonia-R1-24B-v4.1
+base_model_relation: quantized
+---
+
+## Llamacpp imatrix Quantizations of Cydonia-R1-24B-v4.1 by TheDrummer
+
+Using <a href="https://github.com/ggml-org/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggml-org/llama.cpp/releases/tag/b6550">b6550</a> for quantization.
+
+Original model: https://huggingface.co/TheDrummer/Cydonia-R1-24B-v4.1
+
+All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8) combined with a subset of combined_all_small.parquet from Ed Addario [here](https://huggingface.co/datasets/eaddario/imatrix-calibration/blob/main/combined_all_small.parquet)
+
+Run them in [LM Studio](https://lmstudio.ai/)
+
+Run them directly with [llama.cpp](https://github.com/ggml-org/llama.cpp), or any other llama.cpp based project
+
+## Prompt format
+
+No prompt format found, check original model page
+
+## Download a file (not the whole branch) from below:
+
+| Filename | Quant type | File Size | Split | Description |
+| -------- | ---------- | --------- | ----- | ----------- |
+| [Cydonia-R1-24B-v4.1-bf16.gguf](https://huggingface.co/bartowski/TheDrummer_Cydonia-R1-24B-v4.1-GGUF/blob/main/TheDrummer_Cydonia-R1-24B-v4.1-bf16.gguf) | bf16 | 47.15GB | false | Full BF16 weights. |
+| [Cydonia-R1-24B-v4.1-Q8_0.gguf](https://huggingface.co/bartowski/TheDrummer_Cydonia-R1-24B-v4.1-GGUF/blob/main/TheDrummer_Cydonia-R1-24B-v4.1-Q8_0.gguf) | Q8_0 | 25.05GB | false | Extremely high quality, generally unneeded but max available quant. |
+| [Cydonia-R1-24B-v4.1-Q6_K_L.gguf](https://huggingface.co/bartowski/TheDrummer_Cydonia-R1-24B-v4.1-GGUF/blob/main/TheDrummer_Cydonia-R1-24B-v4.1-Q6_K_L.gguf) | Q6_K_L | 19.67GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
+| [Cydonia-R1-24B-v4.1-Q6_K.gguf](https://huggingface.co/bartowski/TheDrummer_Cydonia-R1-24B-v4.1-GGUF/blob/main/TheDrummer_Cydonia-R1-24B-v4.1-Q6_K.gguf) | Q6_K | 19.35GB | false | Very high quality, near perfect, *recommended*. |
+| [Cydonia-R1-24B-v4.1-Q5_K_L.gguf](https://huggingface.co/bartowski/TheDrummer_Cydonia-R1-24B-v4.1-GGUF/blob/main/TheDrummer_Cydonia-R1-24B-v4.1-Q5_K_L.gguf) | Q5_K_L | 17.18GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
+| [Cydonia-R1-24B-v4.1-Q5_K_M.gguf](https://huggingface.co/bartowski/TheDrummer_Cydonia-R1-24B-v4.1-GGUF/blob/main/TheDrummer_Cydonia-R1-24B-v4.1-Q5_K_M.gguf) | Q5_K_M | 16.76GB | false | High quality, *recommended*. |
+| [Cydonia-R1-24B-v4.1-Q5_K_S.gguf](https://huggingface.co/bartowski/TheDrummer_Cydonia-R1-24B-v4.1-GGUF/blob/main/TheDrummer_Cydonia-R1-24B-v4.1-Q5_K_S.gguf) | Q5_K_S | 16.30GB | false | High quality, *recommended*. |
+| [Cydonia-R1-24B-v4.1-Q4_1.gguf](https://huggingface.co/bartowski/TheDrummer_Cydonia-R1-24B-v4.1-GGUF/blob/main/TheDrummer_Cydonia-R1-24B-v4.1-Q4_1.gguf) | Q4_1 | 14.87GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
+| [Cydonia-R1-24B-v4.1-Q4_K_L.gguf](https://huggingface.co/bartowski/TheDrummer_Cydonia-R1-24B-v4.1-GGUF/blob/main/TheDrummer_Cydonia-R1-24B-v4.1-Q4_K_L.gguf) | Q4_K_L | 14.83GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
+| [Cydonia-R1-24B-v4.1-Q4_K_M.gguf](https://huggingface.co/bartowski/TheDrummer_Cydonia-R1-24B-v4.1-GGUF/blob/main/TheDrummer_Cydonia-R1-24B-v4.1-Q4_K_M.gguf) | Q4_K_M | 14.33GB | false | Good quality, default size for most use cases, *recommended*. |
+| [Cydonia-R1-24B-v4.1-Q4_K_S.gguf](https://huggingface.co/bartowski/TheDrummer_Cydonia-R1-24B-v4.1-GGUF/blob/main/TheDrummer_Cydonia-R1-24B-v4.1-Q4_K_S.gguf) | Q4_K_S | 13.55GB | false | Slightly lower quality with more space savings, *recommended*. |
+| [Cydonia-R1-24B-v4.1-Q4_0.gguf](https://huggingface.co/bartowski/TheDrummer_Cydonia-R1-24B-v4.1-GGUF/blob/main/TheDrummer_Cydonia-R1-24B-v4.1-Q4_0.gguf) | Q4_0 | 13.49GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
+| [Cydonia-R1-24B-v4.1-IQ4_NL.gguf](https://huggingface.co/bartowski/TheDrummer_Cydonia-R1-24B-v4.1-GGUF/blob/main/TheDrummer_Cydonia-R1-24B-v4.1-IQ4_NL.gguf) | IQ4_NL | 13.47GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
+| [Cydonia-R1-24B-v4.1-Q3_K_XL.gguf](https://huggingface.co/bartowski/TheDrummer_Cydonia-R1-24B-v4.1-GGUF/blob/main/TheDrummer_Cydonia-R1-24B-v4.1-Q3_K_XL.gguf) | Q3_K_XL | 12.99GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
+| [Cydonia-R1-24B-v4.1-IQ4_XS.gguf](https://huggingface.co/bartowski/TheDrummer_Cydonia-R1-24B-v4.1-GGUF/blob/main/TheDrummer_Cydonia-R1-24B-v4.1-IQ4_XS.gguf) | IQ4_XS | 12.76GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
+| [Cydonia-R1-24B-v4.1-Q3_K_L.gguf](https://huggingface.co/bartowski/TheDrummer_Cydonia-R1-24B-v4.1-GGUF/blob/main/TheDrummer_Cydonia-R1-24B-v4.1-Q3_K_L.gguf) | Q3_K_L | 12.40GB | false | Lower quality but usable, good for low RAM availability. |
+| [Cydonia-R1-24B-v4.1-Q3_K_M.gguf](https://huggingface.co/bartowski/TheDrummer_Cydonia-R1-24B-v4.1-GGUF/blob/main/TheDrummer_Cydonia-R1-24B-v4.1-Q3_K_M.gguf) | Q3_K_M | 11.47GB | false | Low quality. |
+| [Cydonia-R1-24B-v4.1-IQ3_M.gguf](https://huggingface.co/bartowski/TheDrummer_Cydonia-R1-24B-v4.1-GGUF/blob/main/TheDrummer_Cydonia-R1-24B-v4.1-IQ3_M.gguf) | IQ3_M | 10.65GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
+| [Cydonia-R1-24B-v4.1-Q3_K_S.gguf](https://huggingface.co/bartowski/TheDrummer_Cydonia-R1-24B-v4.1-GGUF/blob/main/TheDrummer_Cydonia-R1-24B-v4.1-Q3_K_S.gguf) | Q3_K_S | 10.40GB | false | Low quality, not recommended. |
+| [Cydonia-R1-24B-v4.1-IQ3_XS.gguf](https://huggingface.co/bartowski/TheDrummer_Cydonia-R1-24B-v4.1-GGUF/blob/main/TheDrummer_Cydonia-R1-24B-v4.1-IQ3_XS.gguf) | IQ3_XS | 9.91GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
+| [Cydonia-R1-24B-v4.1-Q2_K_L.gguf](https://huggingface.co/bartowski/TheDrummer_Cydonia-R1-24B-v4.1-GGUF/blob/main/TheDrummer_Cydonia-R1-24B-v4.1-Q2_K_L.gguf) | Q2_K_L | 9.55GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
+| [Cydonia-R1-24B-v4.1-IQ3_XXS.gguf](https://huggingface.co/bartowski/TheDrummer_Cydonia-R1-24B-v4.1-GGUF/blob/main/TheDrummer_Cydonia-R1-24B-v4.1-IQ3_XXS.gguf) | IQ3_XXS | 9.28GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
+| [Cydonia-R1-24B-v4.1-Q2_K.gguf](https://huggingface.co/bartowski/TheDrummer_Cydonia-R1-24B-v4.1-GGUF/blob/main/TheDrummer_Cydonia-R1-24B-v4.1-Q2_K.gguf) | Q2_K | 8.89GB | false | Very low quality but surprisingly usable. |
+| [Cydonia-R1-24B-v4.1-IQ2_M.gguf](https://huggingface.co/bartowski/TheDrummer_Cydonia-R1-24B-v4.1-GGUF/blob/main/TheDrummer_Cydonia-R1-24B-v4.1-IQ2_M.gguf) | IQ2_M | 8.11GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
+| [Cydonia-R1-24B-v4.1-IQ2_S.gguf](https://huggingface.co/bartowski/TheDrummer_Cydonia-R1-24B-v4.1-GGUF/blob/main/TheDrummer_Cydonia-R1-24B-v4.1-IQ2_S.gguf) | IQ2_S | 7.48GB | false | Low quality, uses SOTA techniques to be usable. |
+| [Cydonia-R1-24B-v4.1-IQ2_XS.gguf](https://huggingface.co/bartowski/TheDrummer_Cydonia-R1-24B-v4.1-GGUF/blob/main/TheDrummer_Cydonia-R1-24B-v4.1-IQ2_XS.gguf) | IQ2_XS | 7.21GB | 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/TheDrummer_Cydonia-R1-24B-v4.1-GGUF --include "TheDrummer_Cydonia-R1-24B-v4.1-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/TheDrummer_Cydonia-R1-24B-v4.1-GGUF --include "TheDrummer_Cydonia-R1-24B-v4.1-Q8_0/*" --local-dir ./
+```
+
+You can either specify a new local-dir (TheDrummer_Cydonia-R1-24B-v4.1-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/ggml-org/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/ggml-org/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/ggml-org/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/ggml-org/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

TheDrummer_Cydonia-R1-24B-v4.1-IQ2_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d0c6e7007ef6c58ac763b208505a8a7509965718e58817b78c857855cd001d2
+size 8114052512

TheDrummer_Cydonia-R1-24B-v4.1-IQ2_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60d95375e290c0158695d505490918a77b915143a13d05425114da657f8e1e6c
+size 7478353312

TheDrummer_Cydonia-R1-24B-v4.1-IQ2_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6efca8178c9b3e218e5885a8f867933af6a3a1ecce61a8c48816293bbacebd0a
+size 7207034272

TheDrummer_Cydonia-R1-24B-v4.1-IQ3_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fb8f7f01d5a8528ec0abeeed48c94547fc8aa2487d337e4af4b831cf78b72eb
+size 10650951072

TheDrummer_Cydonia-R1-24B-v4.1-IQ3_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f5ef8de3b1cde18b80fce9f5632e842979bdd5f68654a5623a5c80180c10d53
+size 9907117472

TheDrummer_Cydonia-R1-24B-v4.1-IQ3_XXS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b45bc26cb096e0bd15507ab097ee792edf6d51133de69b666df790b3239cea8d
+size 9280593312

TheDrummer_Cydonia-R1-24B-v4.1-IQ4_NL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4086e0fe6b28b54c8ed2f6e833683a49a01a46734c45155e3036fae45dc21192
+size 13468016032

TheDrummer_Cydonia-R1-24B-v4.1-IQ4_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4e0ab8cab9f7e6f08e2ec63b472190d78983f086dc73a1ec17b9c2619ea0f6b
+size 12758916512

TheDrummer_Cydonia-R1-24B-v4.1-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df2d177db270b1b23d137082ca22760731e11df091f45634dcb986900c642ccb
+size 8890326432

TheDrummer_Cydonia-R1-24B-v4.1-Q2_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe7cd94f459eab967e29ee51495a98a5ccb1f86ec02d500905674e382910a836
+size 9545686432

TheDrummer_Cydonia-R1-24B-v4.1-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27739a97b69380b5971536e71344a037ad345bf36a554cb22c11cd6a8f9e2101
+size 12400762272

TheDrummer_Cydonia-R1-24B-v4.1-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49f8e2e7004cc15990d57583bb5e1dac9519bca31d82db20a6d00a88aa56bde9
+size 11474083232

TheDrummer_Cydonia-R1-24B-v4.1-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab4dd621c75929f694971f9c94bac6b83930174fb92617f2e7d39561ccb23164
+size 10400275872

TheDrummer_Cydonia-R1-24B-v4.1-Q3_K_XL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dec7f7bfbc6df0f3472e493df39f739c02a472d4327072a53a09351c85aeef0
+size 12987964832

TheDrummer_Cydonia-R1-24B-v4.1-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddbeb0c08e8f6059ee2060125a79ba07d50ae5539f13df47c14e5fe265f8bd6e
+size 13494230432

TheDrummer_Cydonia-R1-24B-v4.1-Q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:787224eabc4c2f071b63ac2cfb1f708b40dc32cb9b2487af4a4489ee633c4c2b
+size 14873107872

TheDrummer_Cydonia-R1-24B-v4.1-Q4_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a3d29b10fc8a62a5f3b689942d529e93e9d23674c7579ca5affef17b287f62e
+size 14831984032

TheDrummer_Cydonia-R1-24B-v4.1-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d4e0dc339851fd96da544e311b2a8962b3ebb8f5792799f9571721c0fb49893
+size 14333910432

TheDrummer_Cydonia-R1-24B-v4.1-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7c751919cad3c35ea2e6010b89bd19b96f00bcddff88df91aee95233aca953d
+size 13549280672

TheDrummer_Cydonia-R1-24B-v4.1-Q5_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2241fa9f381ee3bcab824db0d5f379a0075c934d84ddf11ea7f3f7190b7849a9
+size 17178172832

TheDrummer_Cydonia-R1-24B-v4.1-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d344a869fdcd010fe039e0ea94615515bc5be859c8e558c01a3e6ebd4527ea59
+size 16763985312

TheDrummer_Cydonia-R1-24B-v4.1-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4760f1714299e6813cd0b78aaacec3539c2806563eed193a480f690ff850ab6
+size 16304414112

TheDrummer_Cydonia-R1-24B-v4.1-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b85877432efb56584b493a898ecb6eaacbf0bfb40317f48f3293c762fb7613f4
+size 19345939872

TheDrummer_Cydonia-R1-24B-v4.1-Q6_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f436c0879fd10d70a5fb17bcddbb571a73bb90dc4697886840be6131709ec59
+size 19670998432

TheDrummer_Cydonia-R1-24B-v4.1-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98b9dd15393c7beea8e20fa89c4e3b10e731068bfc8f62e61796b5d15451a354
+size 25054780832

TheDrummer_Cydonia-R1-24B-v4.1-bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8bbcf14f138a6632d99ac83d3ea5574a29935c591695bd5757212ee54bad521
+size 47153519744

TheDrummer_Cydonia-R1-24B-v4.1-imatrix.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f022169f9135f60db599048eb4b20e530f11ec9c4e55160c8cc08482a057daa
+size 10037344

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}