初始化项目，由ModelHub XC社区提供模型

Model: bartowski/swiss-ai_Apertus-8B-Instruct-2509-GGUF
Source: Original Platform

.gitattributes

@@ -0,0 +1,73 @@
+*.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
+
+swiss-ai_Apertus-8B-Instruct-2509-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+swiss-ai_Apertus-8B-Instruct-2509-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+swiss-ai_Apertus-8B-Instruct-2509-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+swiss-ai_Apertus-8B-Instruct-2509-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
+swiss-ai_Apertus-8B-Instruct-2509-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
+swiss-ai_Apertus-8B-Instruct-2509-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+swiss-ai_Apertus-8B-Instruct-2509-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+swiss-ai_Apertus-8B-Instruct-2509-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
+swiss-ai_Apertus-8B-Instruct-2509-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+swiss-ai_Apertus-8B-Instruct-2509-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+swiss-ai_Apertus-8B-Instruct-2509-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+swiss-ai_Apertus-8B-Instruct-2509-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
+swiss-ai_Apertus-8B-Instruct-2509-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
+swiss-ai_Apertus-8B-Instruct-2509-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+swiss-ai_Apertus-8B-Instruct-2509-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+swiss-ai_Apertus-8B-Instruct-2509-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+swiss-ai_Apertus-8B-Instruct-2509-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+swiss-ai_Apertus-8B-Instruct-2509-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+swiss-ai_Apertus-8B-Instruct-2509-imatrix.gguf filter=lfs diff=lfs merge=lfs -text
+swiss-ai_Apertus-8B-Instruct-2509-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+swiss-ai_Apertus-8B-Instruct-2509-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+swiss-ai_Apertus-8B-Instruct-2509-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+swiss-ai_Apertus-8B-Instruct-2509-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+swiss-ai_Apertus-8B-Instruct-2509-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+swiss-ai_Apertus-8B-Instruct-2509-bf16.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,164 @@
+---
+quantized_by: bartowski
+pipeline_tag: text-generation
+base_model_relation: quantized
+base_model: swiss-ai/Apertus-8B-Instruct-2509
+---
+
+## Llamacpp imatrix Quantizations of Apertus-8B-Instruct-2509 by swiss-ai
+
+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/b6683">b6683</a> for quantization.
+
+Original model: https://huggingface.co/swiss-ai/Apertus-8B-Instruct-2509
+
+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 |
+| -------- | ---------- | --------- | ----- | ----------- |
+| [Apertus-8B-Instruct-2509-bf16.gguf](https://huggingface.co/bartowski/swiss-ai_Apertus-8B-Instruct-2509-GGUF/blob/main/swiss-ai_Apertus-8B-Instruct-2509-bf16.gguf) | bf16 | 16.12GB | false | Full BF16 weights. |
+| [Apertus-8B-Instruct-2509-Q8_0.gguf](https://huggingface.co/bartowski/swiss-ai_Apertus-8B-Instruct-2509-GGUF/blob/main/swiss-ai_Apertus-8B-Instruct-2509-Q8_0.gguf) | Q8_0 | 8.57GB | false | Extremely high quality, generally unneeded but max available quant. |
+| [Apertus-8B-Instruct-2509-Q6_K_L.gguf](https://huggingface.co/bartowski/swiss-ai_Apertus-8B-Instruct-2509-GGUF/blob/main/swiss-ai_Apertus-8B-Instruct-2509-Q6_K_L.gguf) | Q6_K_L | 6.88GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
+| [Apertus-8B-Instruct-2509-Q6_K.gguf](https://huggingface.co/bartowski/swiss-ai_Apertus-8B-Instruct-2509-GGUF/blob/main/swiss-ai_Apertus-8B-Instruct-2509-Q6_K.gguf) | Q6_K | 6.62GB | false | Very high quality, near perfect, *recommended*. |
+| [Apertus-8B-Instruct-2509-Q5_K_L.gguf](https://huggingface.co/bartowski/swiss-ai_Apertus-8B-Instruct-2509-GGUF/blob/main/swiss-ai_Apertus-8B-Instruct-2509-Q5_K_L.gguf) | Q5_K_L | 6.14GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
+| [Apertus-8B-Instruct-2509-Q5_K_M.gguf](https://huggingface.co/bartowski/swiss-ai_Apertus-8B-Instruct-2509-GGUF/blob/main/swiss-ai_Apertus-8B-Instruct-2509-Q5_K_M.gguf) | Q5_K_M | 5.81GB | false | High quality, *recommended*. |
+| [Apertus-8B-Instruct-2509-Q5_K_S.gguf](https://huggingface.co/bartowski/swiss-ai_Apertus-8B-Instruct-2509-GGUF/blob/main/swiss-ai_Apertus-8B-Instruct-2509-Q5_K_S.gguf) | Q5_K_S | 5.62GB | false | High quality, *recommended*. |
+| [Apertus-8B-Instruct-2509-Q4_K_L.gguf](https://huggingface.co/bartowski/swiss-ai_Apertus-8B-Instruct-2509-GGUF/blob/main/swiss-ai_Apertus-8B-Instruct-2509-Q4_K_L.gguf) | Q4_K_L | 5.46GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
+| [Apertus-8B-Instruct-2509-Q4_1.gguf](https://huggingface.co/bartowski/swiss-ai_Apertus-8B-Instruct-2509-GGUF/blob/main/swiss-ai_Apertus-8B-Instruct-2509-Q4_1.gguf) | Q4_1 | 5.15GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
+| [Apertus-8B-Instruct-2509-Q4_K_M.gguf](https://huggingface.co/bartowski/swiss-ai_Apertus-8B-Instruct-2509-GGUF/blob/main/swiss-ai_Apertus-8B-Instruct-2509-Q4_K_M.gguf) | Q4_K_M | 5.06GB | false | Good quality, default size for most use cases, *recommended*. |
+| [Apertus-8B-Instruct-2509-Q3_K_XL.gguf](https://huggingface.co/bartowski/swiss-ai_Apertus-8B-Instruct-2509-GGUF/blob/main/swiss-ai_Apertus-8B-Instruct-2509-Q3_K_XL.gguf) | Q3_K_XL | 5.05GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
+| [Apertus-8B-Instruct-2509-Q4_K_S.gguf](https://huggingface.co/bartowski/swiss-ai_Apertus-8B-Instruct-2509-GGUF/blob/main/swiss-ai_Apertus-8B-Instruct-2509-Q4_K_S.gguf) | Q4_K_S | 4.72GB | false | Slightly lower quality with more space savings, *recommended*. |
+| [Apertus-8B-Instruct-2509-Q4_0.gguf](https://huggingface.co/bartowski/swiss-ai_Apertus-8B-Instruct-2509-GGUF/blob/main/swiss-ai_Apertus-8B-Instruct-2509-Q4_0.gguf) | Q4_0 | 4.70GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
+| [Apertus-8B-Instruct-2509-IQ4_NL.gguf](https://huggingface.co/bartowski/swiss-ai_Apertus-8B-Instruct-2509-GGUF/blob/main/swiss-ai_Apertus-8B-Instruct-2509-IQ4_NL.gguf) | IQ4_NL | 4.69GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
+| [Apertus-8B-Instruct-2509-Q3_K_L.gguf](https://huggingface.co/bartowski/swiss-ai_Apertus-8B-Instruct-2509-GGUF/blob/main/swiss-ai_Apertus-8B-Instruct-2509-Q3_K_L.gguf) | Q3_K_L | 4.58GB | false | Lower quality but usable, good for low RAM availability. |
+| [Apertus-8B-Instruct-2509-IQ4_XS.gguf](https://huggingface.co/bartowski/swiss-ai_Apertus-8B-Instruct-2509-GGUF/blob/main/swiss-ai_Apertus-8B-Instruct-2509-IQ4_XS.gguf) | IQ4_XS | 4.46GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
+| [Apertus-8B-Instruct-2509-Q3_K_M.gguf](https://huggingface.co/bartowski/swiss-ai_Apertus-8B-Instruct-2509-GGUF/blob/main/swiss-ai_Apertus-8B-Instruct-2509-Q3_K_M.gguf) | Q3_K_M | 4.17GB | false | Low quality. |
+| [Apertus-8B-Instruct-2509-IQ3_M.gguf](https://huggingface.co/bartowski/swiss-ai_Apertus-8B-Instruct-2509-GGUF/blob/main/swiss-ai_Apertus-8B-Instruct-2509-IQ3_M.gguf) | IQ3_M | 3.81GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
+| [Apertus-8B-Instruct-2509-Q2_K_L.gguf](https://huggingface.co/bartowski/swiss-ai_Apertus-8B-Instruct-2509-GGUF/blob/main/swiss-ai_Apertus-8B-Instruct-2509-Q2_K_L.gguf) | Q2_K_L | 3.81GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
+| [Apertus-8B-Instruct-2509-Q3_K_S.gguf](https://huggingface.co/bartowski/swiss-ai_Apertus-8B-Instruct-2509-GGUF/blob/main/swiss-ai_Apertus-8B-Instruct-2509-Q3_K_S.gguf) | Q3_K_S | 3.68GB | false | Low quality, not recommended. |
+| [Apertus-8B-Instruct-2509-IQ3_XS.gguf](https://huggingface.co/bartowski/swiss-ai_Apertus-8B-Instruct-2509-GGUF/blob/main/swiss-ai_Apertus-8B-Instruct-2509-IQ3_XS.gguf) | IQ3_XS | 3.57GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
+| [Apertus-8B-Instruct-2509-IQ3_XXS.gguf](https://huggingface.co/bartowski/swiss-ai_Apertus-8B-Instruct-2509-GGUF/blob/main/swiss-ai_Apertus-8B-Instruct-2509-IQ3_XXS.gguf) | IQ3_XXS | 3.29GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
+| [Apertus-8B-Instruct-2509-Q2_K.gguf](https://huggingface.co/bartowski/swiss-ai_Apertus-8B-Instruct-2509-GGUF/blob/main/swiss-ai_Apertus-8B-Instruct-2509-Q2_K.gguf) | Q2_K | 3.29GB | false | Very low quality but surprisingly usable. |
+| [Apertus-8B-Instruct-2509-IQ2_M.gguf](https://huggingface.co/bartowski/swiss-ai_Apertus-8B-Instruct-2509-GGUF/blob/main/swiss-ai_Apertus-8B-Instruct-2509-IQ2_M.gguf) | IQ2_M | 2.97GB | false | Relatively low quality, uses SOTA techniques to be surprisingly 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/swiss-ai_Apertus-8B-Instruct-2509-GGUF --include "swiss-ai_Apertus-8B-Instruct-2509-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/swiss-ai_Apertus-8B-Instruct-2509-GGUF --include "swiss-ai_Apertus-8B-Instruct-2509-Q8_0/*" --local-dir ./
+```
+
+You can either specify a new local-dir (swiss-ai_Apertus-8B-Instruct-2509-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

configuration.json

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

swiss-ai_Apertus-8B-Instruct-2509-IQ2_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14fb4c64f7d6ba218422da727df5e9bc6d0b95e5631bd923bb68f3911d6a309a
+size 2974102912

swiss-ai_Apertus-8B-Instruct-2509-IQ3_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:200825f10ad6baaaf383e02dfc074b82e9edbab9471112fd5bbe7b85821cd67c
+size 3814929792

swiss-ai_Apertus-8B-Instruct-2509-IQ3_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28496dd890d8b72ecdf3961412e16fe742ec5114e68a49a875ef6470be9539a9
+size 3566286208

swiss-ai_Apertus-8B-Instruct-2509-IQ3_XXS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9db2ee6afb31e687fcbd7034240410966ba566175597d522a227d814d6c1e6c3
+size 3287889280

swiss-ai_Apertus-8B-Instruct-2509-IQ4_NL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6d5c7474d97bf63e27cfb5e3b1ab8bbfad53e0a9d4f77f8e8fadef91736c232
+size 4694029696

swiss-ai_Apertus-8B-Instruct-2509-IQ4_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3fd181089e743521c1259b0c30f1ad04606505dcb515755384bf5c95e9da6e3
+size 4463342976

swiss-ai_Apertus-8B-Instruct-2509-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ba1097219728b94f5cd543035bd6d76ea3264006c58ab07e71d2c9c0266b22b
+size 3287889280

swiss-ai_Apertus-8B-Instruct-2509-Q2_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20cfb84b6543a0fa989febd29482027ca4b069eae80eb265fe5aebd81e45064d
+size 3812177280

swiss-ai_Apertus-8B-Instruct-2509-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55afd34c92a910a91f726c72d4979d391e4b9e8778dfd637e86cbcd12b1bcd31
+size 4578686336

swiss-ai_Apertus-8B-Instruct-2509-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3927b30bec142049cec675492590a42cb9247aad30fb8e5b356ce4aa1924d1e
+size 4165547392

swiss-ai_Apertus-8B-Instruct-2509-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73784c4012f757537416308f654f14400db9707affbbbdf3974ffdc928c3c5b6
+size 3679008128

swiss-ai_Apertus-8B-Instruct-2509-Q3_K_XL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30b72f2431573bacfa3d425bd00ee586f49f2143878ca8e3f7c7381836a6573f
+size 5048448384

swiss-ai_Apertus-8B-Instruct-2509-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e6864c16d20e1a43802b8503f71f23508d75c47c3f3c2f352d7e5982b4e618e
+size 4699272576

swiss-ai_Apertus-8B-Instruct-2509-Q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:345a8669d04829c22b1888d4aaee5308cc626f7ec72b158064197c3bb930a139
+size 5147014528

swiss-ai_Apertus-8B-Instruct-2509-Q4_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00932fc56d43fcd2295c6ff85112989fb43d3cdd7f010813d62d7f8173f18fd8
+size 5456344448

swiss-ai_Apertus-8B-Instruct-2509-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5901007f15aec9aabeea401cbe65559671166fc851bbdf8c26f56c2b61e9cd1d
+size 5057885568

swiss-ai_Apertus-8B-Instruct-2509-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e9f332faa0e877b07f853a29233116c6eff0b7862492e16d252f62d4e53f84f
+size 4723389824

swiss-ai_Apertus-8B-Instruct-2509-Q5_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1801caa51c9235146b888729167046e5714e3535e3a01d26a25d43b45aaa049
+size 6144210304

swiss-ai_Apertus-8B-Instruct-2509-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66923711c06a3a8f763a7b51891665b89aba3876dc5e9230eb9f6b0fc662ce23
+size 5812860288

swiss-ai_Apertus-8B-Instruct-2509-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:121dfc93910a82f508b35bd63916a92d11a1cee7394ad2386ed52c4e1207e6ae
+size 5616776576

swiss-ai_Apertus-8B-Instruct-2509-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a69ef6d82b1ed7be0d6c41f31b6ddd114ccfba454fd41e7cfa17ee9978bad53f
+size 6615020928

swiss-ai_Apertus-8B-Instruct-2509-Q6_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89f4c6c58fcb0e3e715043e0167d5ba7c0bf2da4882ec104d900528d4777ddb7
+size 6875067776

swiss-ai_Apertus-8B-Instruct-2509-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68a9d338961e9cc47362649e703fd67b4f4eb616a16d97b9c2c458aea4e3db7a
+size 8565372288

swiss-ai_Apertus-8B-Instruct-2509-bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de9ac43f177e0698c936107ad66f4de0a2eba7f67e2eb104aef7111edb4766a0
+size 16115119168

swiss-ai_Apertus-8B-Instruct-2509-imatrix.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4e1b53fde4797e88d09d43af780b3c1bb88f93853e9c45d4249160cd95455ca
+size 5403488