初始化项目，由ModelHub XC社区提供模型

Model: bartowski/nvidia_Nemotron-Cascade-14B-Thinking-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
+ 
+*.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
+
+nvidia_Nemotron-Cascade-14B-Thinking-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-14B-Thinking-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-14B-Thinking-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-14B-Thinking-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-14B-Thinking-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-14B-Thinking-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-14B-Thinking-bf16.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-14B-Thinking-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-14B-Thinking-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-14B-Thinking-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-14B-Thinking-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-14B-Thinking-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-14B-Thinking-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-14B-Thinking-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-14B-Thinking-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-14B-Thinking-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-14B-Thinking-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-14B-Thinking-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-14B-Thinking-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-14B-Thinking-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-14B-Thinking-imatrix.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-14B-Thinking-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-14B-Thinking-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-14B-Thinking-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-14B-Thinking-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-14B-Thinking-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-14B-Thinking-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,184 @@
+---
+quantized_by: bartowski
+pipeline_tag: text-generation
+tags:
+- nvidia
+- nemotron-cascade
+- reasoning
+- general-purpose
+- SFT
+- RL
+license: other
+license_name: nvidia-open-model-license
+language:
+- en
+base_model: nvidia/Nemotron-Cascade-14B-Thinking
+base_model_relation: quantized
+license_link: https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/
+---
+
+## Llamacpp imatrix Quantizations of Nemotron-Cascade-14B-Thinking by nvidia
+
+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/b7423">b7423</a> for quantization.
+
+Original model: https://huggingface.co/nvidia/Nemotron-Cascade-14B-Thinking
+
+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
+
+```
+<|im_start|>system
+{system_prompt}<|im_end|>
+<|im_start|>user
+{prompt} /think<|im_end|>
+<|im_start|>assistant
+```
+
+## Download a file (not the whole branch) from below:
+
+| Filename | Quant type | File Size | Split | Description |
+| -------- | ---------- | --------- | ----- | ----------- |
+| [Nemotron-Cascade-14B-Thinking-bf16.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-14B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-14B-Thinking-bf16.gguf) | bf16 | 29.54GB | false | Full BF16 weights. |
+| [Nemotron-Cascade-14B-Thinking-Q8_0.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-14B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-14B-Thinking-Q8_0.gguf) | Q8_0 | 15.70GB | false | Extremely high quality, generally unneeded but max available quant. |
+| [Nemotron-Cascade-14B-Thinking-Q6_K_L.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-14B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-14B-Thinking-Q6_K_L.gguf) | Q6_K_L | 12.50GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
+| [Nemotron-Cascade-14B-Thinking-Q6_K.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-14B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-14B-Thinking-Q6_K.gguf) | Q6_K | 12.12GB | false | Very high quality, near perfect, *recommended*. |
+| [Nemotron-Cascade-14B-Thinking-Q5_K_L.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-14B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-14B-Thinking-Q5_K_L.gguf) | Q5_K_L | 10.99GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
+| [Nemotron-Cascade-14B-Thinking-Q5_K_M.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-14B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-14B-Thinking-Q5_K_M.gguf) | Q5_K_M | 10.51GB | false | High quality, *recommended*. |
+| [Nemotron-Cascade-14B-Thinking-Q5_K_S.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-14B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-14B-Thinking-Q5_K_S.gguf) | Q5_K_S | 10.26GB | false | High quality, *recommended*. |
+| [Nemotron-Cascade-14B-Thinking-Q4_K_L.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-14B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-14B-Thinking-Q4_K_L.gguf) | Q4_K_L | 9.58GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
+| [Nemotron-Cascade-14B-Thinking-Q4_1.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-14B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-14B-Thinking-Q4_1.gguf) | Q4_1 | 9.39GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
+| [Nemotron-Cascade-14B-Thinking-Q4_K_M.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-14B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-14B-Thinking-Q4_K_M.gguf) | Q4_K_M | 9.00GB | false | Good quality, default size for most use cases, *recommended*. |
+| [Nemotron-Cascade-14B-Thinking-Q3_K_XL.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-14B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-14B-Thinking-Q3_K_XL.gguf) | Q3_K_XL | 8.58GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
+| [Nemotron-Cascade-14B-Thinking-Q4_K_S.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-14B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-14B-Thinking-Q4_K_S.gguf) | Q4_K_S | 8.57GB | false | Slightly lower quality with more space savings, *recommended*. |
+| [Nemotron-Cascade-14B-Thinking-Q4_0.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-14B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-14B-Thinking-Q4_0.gguf) | Q4_0 | 8.54GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
+| [Nemotron-Cascade-14B-Thinking-IQ4_NL.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-14B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-14B-Thinking-IQ4_NL.gguf) | IQ4_NL | 8.54GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
+| [Nemotron-Cascade-14B-Thinking-IQ4_XS.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-14B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-14B-Thinking-IQ4_XS.gguf) | IQ4_XS | 8.11GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
+| [Nemotron-Cascade-14B-Thinking-Q3_K_L.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-14B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-14B-Thinking-Q3_K_L.gguf) | Q3_K_L | 7.90GB | false | Lower quality but usable, good for low RAM availability. |
+| [Nemotron-Cascade-14B-Thinking-Q3_K_M.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-14B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-14B-Thinking-Q3_K_M.gguf) | Q3_K_M | 7.32GB | false | Low quality. |
+| [Nemotron-Cascade-14B-Thinking-IQ3_M.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-14B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-14B-Thinking-IQ3_M.gguf) | IQ3_M | 6.88GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
+| [Nemotron-Cascade-14B-Thinking-Q3_K_S.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-14B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-14B-Thinking-Q3_K_S.gguf) | Q3_K_S | 6.66GB | false | Low quality, not recommended. |
+| [Nemotron-Cascade-14B-Thinking-Q2_K_L.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-14B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-14B-Thinking-Q2_K_L.gguf) | Q2_K_L | 6.51GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
+| [Nemotron-Cascade-14B-Thinking-IQ3_XS.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-14B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-14B-Thinking-IQ3_XS.gguf) | IQ3_XS | 6.38GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
+| [Nemotron-Cascade-14B-Thinking-IQ3_XXS.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-14B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-14B-Thinking-IQ3_XXS.gguf) | IQ3_XXS | 5.94GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
+| [Nemotron-Cascade-14B-Thinking-Q2_K.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-14B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-14B-Thinking-Q2_K.gguf) | Q2_K | 5.75GB | false | Very low quality but surprisingly usable. |
+| [Nemotron-Cascade-14B-Thinking-IQ2_M.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-14B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-14B-Thinking-IQ2_M.gguf) | IQ2_M | 5.32GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
+| [Nemotron-Cascade-14B-Thinking-IQ2_S.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-14B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-14B-Thinking-IQ2_S.gguf) | IQ2_S | 4.96GB | false | Low quality, uses SOTA techniques to be usable. |
+| [Nemotron-Cascade-14B-Thinking-IQ2_XS.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-14B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-14B-Thinking-IQ2_XS.gguf) | IQ2_XS | 4.69GB | 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/nvidia_Nemotron-Cascade-14B-Thinking-GGUF --include "nvidia_Nemotron-Cascade-14B-Thinking-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/nvidia_Nemotron-Cascade-14B-Thinking-GGUF --include "nvidia_Nemotron-Cascade-14B-Thinking-Q8_0/*" --local-dir ./
+```
+
+You can either specify a new local-dir (nvidia_Nemotron-Cascade-14B-Thinking-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}

nvidia_Nemotron-Cascade-14B-Thinking-IQ2_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e7d71678abb9cc24ea049b13a87e40533649f9670a81563cc0a42f3bfd5f1a5
+size 5322942080

nvidia_Nemotron-Cascade-14B-Thinking-IQ2_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0365e192fb522fb14d95789ec3502596d58bbb642abf1d15777c09866baaa1dc
+size 4963313280

nvidia_Nemotron-Cascade-14B-Thinking-IQ2_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d06e90b472f2fb9840db9318e83382c5fcb927c8efb7a0402a3f997a54336a65
+size 4691589760

nvidia_Nemotron-Cascade-14B-Thinking-IQ3_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:025f78b0718f7b3df0a097d57ebdeb681b20a954491d762b043f060f3eecde1f
+size 6883410560

nvidia_Nemotron-Cascade-14B-Thinking-IQ3_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e66d0ffd3c16fc08fcda635350d60c76df1bf7bc3b97dfa058cfe000199468d5
+size 6375301760

nvidia_Nemotron-Cascade-14B-Thinking-IQ3_XXS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:869b931304d697a0aa7e6d134816aba8d850204f58db0c772a2384e556a02e1c
+size 5942666880

nvidia_Nemotron-Cascade-14B-Thinking-IQ4_NL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66bd78af480e8830ad148b3051c989a04b8d6d6c3fd049cf99b8e8e225925ad8
+size 8541363840

nvidia_Nemotron-Cascade-14B-Thinking-IQ4_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5faccd9f87c3766e58e4afa0a49cde647981272f33f6219ec48fc05364a76c2
+size 8110730880

nvidia_Nemotron-Cascade-14B-Thinking-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89b23807c2a0022dfd3f32a72be9d7b683ba56277bebe67ddb7f1757d3a3ce6b
+size 5753984640

nvidia_Nemotron-Cascade-14B-Thinking-Q2_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfb63fb302a42b785bf6e62dbf3832dbb4219d4a16f7541f3d5dac7cdd5d5343
+size 6513664640

nvidia_Nemotron-Cascade-14B-Thinking-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e72d106b5fcf78ed49ae8368a352622849bf06feee3aad132b14a300b3482db
+size 7900652160

nvidia_Nemotron-Cascade-14B-Thinking-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3266092c1cb5ca3655e66dfb6ecde0ab879292f3a401e3b9fed74d3383f17a08
+size 7321313920

nvidia_Nemotron-Cascade-14B-Thinking-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd9eccebd8997e2a37a431b552eec95c6914e3f5c112301624a702537e6eae97
+size 6657106560

nvidia_Nemotron-Cascade-14B-Thinking-Q3_K_XL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36cc41cf93ae4f18970ea3a670377400276ce1886a972a6f15a4417550f7fc9f
+size 8581325440

nvidia_Nemotron-Cascade-14B-Thinking-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ca9fef0378e94a53da4611e3712e3915c3858c5b814c0e60dd5c6c7bec30957
+size 8543002240

nvidia_Nemotron-Cascade-14B-Thinking-Q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d4b9d88e501c0e6d64887970b736197a13d5e96f147b9c93685de682be22af7
+size 9389522560

nvidia_Nemotron-Cascade-14B-Thinking-Q4_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4381f1936520e1fe3e28b8f0a1f69874fe3be824cd5941f7c081a8643e0c87e0
+size 9579111040

nvidia_Nemotron-Cascade-14B-Thinking-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af36aa06103ebf068ddd36d00aba46b3a2a8d448da08f8824fdf8ea4c76a9522
+size 9001754240

nvidia_Nemotron-Cascade-14B-Thinking-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7b61e2698036d8028f868fe06e78712134f6416fb55b2f8b787f8a1f03fa5bc
+size 8573476480

nvidia_Nemotron-Cascade-14B-Thinking-Q5_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b0cf91f28257d9c771b4bbb753dd31ce573fea5f53c3139e7df9c349ecb8031
+size 10994688640

nvidia_Nemotron-Cascade-14B-Thinking-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:964f654b6f573b7552decad7806b7e78b2069874cec47344679c46c2774e1cb7
+size 10514570880

nvidia_Nemotron-Cascade-14B-Thinking-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faed2ee2644539ae728515c4e4ee31452ec96ce48885aac44a85b64eb7f14db0
+size 10263895680

nvidia_Nemotron-Cascade-14B-Thinking-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edcba986796a702287479885c4bc14b59ef52c421bccf149e2bc63f6a397f0de
+size 12121938560

nvidia_Nemotron-Cascade-14B-Thinking-Q6_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfaaf894b67f0d0d8464369e994e9a08b21bddb109370180e2ec793fe9c14575
+size 12498739840

nvidia_Nemotron-Cascade-14B-Thinking-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99c533a14f77d214cd90e1453ecdf0ff7fbf61d189afdf6eb3aa72252258af03
+size 15698535040

nvidia_Nemotron-Cascade-14B-Thinking-bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:694680cdfd023b11df8665a6b8ba7cf62bfac49ba2d6142bc66933cda6d5b7e8
+size 29543424320

nvidia_Nemotron-Cascade-14B-Thinking-imatrix.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cbd679c8f9c5d353205a05bf0cf983b317f3589b15b2706258da007c8e58265
+size 7743584