commit 0fe33c60f054bb2627fdfe3394cac57716a529fe Author: ModelHub XC Date: Fri Jul 31 11:02:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/nvidia_Nemotron-H-8B-Reasoning-128K-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..53d7257 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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 +*.gguf* 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 \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..0bd549b --- /dev/null +++ b/README.md @@ -0,0 +1,164 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +base_model_relation: quantized +base_model: nvidia/Nemotron-H-8B-Reasoning-128K +--- + +## Llamacpp imatrix Quantizations of Nemotron-H-8B-Reasoning-128K by nvidia + +Using llama.cpp release b6317 for quantization. + +Original model: https://huggingface.co/nvidia/Nemotron-H-8B-Reasoning-128K + +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 | +| -------- | ---------- | --------- | ----- | ----------- | +| [Nemotron-H-8B-Reasoning-128K-bf16.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-H-8B-Reasoning-128K-GGUF/blob/main/nvidia_Nemotron-H-8B-Reasoning-128K-bf16.gguf) | bf16 | 16.21GB | false | Full BF16 weights. | +| [Nemotron-H-8B-Reasoning-128K-Q8_0.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-H-8B-Reasoning-128K-GGUF/blob/main/nvidia_Nemotron-H-8B-Reasoning-128K-Q8_0.gguf) | Q8_0 | 8.62GB | false | Extremely high quality, generally unneeded but max available quant. | +| [Nemotron-H-8B-Reasoning-128K-Q6_K_L.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-H-8B-Reasoning-128K-GGUF/blob/main/nvidia_Nemotron-H-8B-Reasoning-128K-Q6_K_L.gguf) | Q6_K_L | 6.92GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [Nemotron-H-8B-Reasoning-128K-Q6_K.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-H-8B-Reasoning-128K-GGUF/blob/main/nvidia_Nemotron-H-8B-Reasoning-128K-Q6_K.gguf) | Q6_K | 6.66GB | false | Very high quality, near perfect, *recommended*. | +| [Nemotron-H-8B-Reasoning-128K-Q5_K_L.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-H-8B-Reasoning-128K-GGUF/blob/main/nvidia_Nemotron-H-8B-Reasoning-128K-Q5_K_L.gguf) | Q5_K_L | 6.13GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [Nemotron-H-8B-Reasoning-128K-Q5_K_M.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-H-8B-Reasoning-128K-GGUF/blob/main/nvidia_Nemotron-H-8B-Reasoning-128K-Q5_K_M.gguf) | Q5_K_M | 5.80GB | false | High quality, *recommended*. | +| [Nemotron-H-8B-Reasoning-128K-Q5_K_S.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-H-8B-Reasoning-128K-GGUF/blob/main/nvidia_Nemotron-H-8B-Reasoning-128K-Q5_K_S.gguf) | Q5_K_S | 5.65GB | false | High quality, *recommended*. | +| [Nemotron-H-8B-Reasoning-128K-Q4_K_L.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-H-8B-Reasoning-128K-GGUF/blob/main/nvidia_Nemotron-H-8B-Reasoning-128K-Q4_K_L.gguf) | Q4_K_L | 5.38GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [Nemotron-H-8B-Reasoning-128K-Q4_1.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-H-8B-Reasoning-128K-GGUF/blob/main/nvidia_Nemotron-H-8B-Reasoning-128K-Q4_1.gguf) | Q4_1 | 5.18GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [Nemotron-H-8B-Reasoning-128K-Q4_K_M.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-H-8B-Reasoning-128K-GGUF/blob/main/nvidia_Nemotron-H-8B-Reasoning-128K-Q4_K_M.gguf) | Q4_K_M | 4.98GB | false | Good quality, default size for most use cases, *recommended*. | +| [Nemotron-H-8B-Reasoning-128K-Q4_K_S.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-H-8B-Reasoning-128K-GGUF/blob/main/nvidia_Nemotron-H-8B-Reasoning-128K-Q4_K_S.gguf) | Q4_K_S | 4.78GB | false | Slightly lower quality with more space savings, *recommended*. | +| [Nemotron-H-8B-Reasoning-128K-Q4_0.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-H-8B-Reasoning-128K-GGUF/blob/main/nvidia_Nemotron-H-8B-Reasoning-128K-Q4_0.gguf) | Q4_0 | 4.74GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [Nemotron-H-8B-Reasoning-128K-Q3_K_XL.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-H-8B-Reasoning-128K-GGUF/blob/main/nvidia_Nemotron-H-8B-Reasoning-128K-Q3_K_XL.gguf) | Q3_K_XL | 4.74GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [Nemotron-H-8B-Reasoning-128K-IQ4_NL.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-H-8B-Reasoning-128K-GGUF/blob/main/nvidia_Nemotron-H-8B-Reasoning-128K-IQ4_NL.gguf) | IQ4_NL | 4.71GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [Nemotron-H-8B-Reasoning-128K-IQ4_XS.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-H-8B-Reasoning-128K-GGUF/blob/main/nvidia_Nemotron-H-8B-Reasoning-128K-IQ4_XS.gguf) | IQ4_XS | 4.47GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [Nemotron-H-8B-Reasoning-128K-Q3_K_L.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-H-8B-Reasoning-128K-GGUF/blob/main/nvidia_Nemotron-H-8B-Reasoning-128K-Q3_K_L.gguf) | Q3_K_L | 4.27GB | false | Lower quality but usable, good for low RAM availability. | +| [Nemotron-H-8B-Reasoning-128K-Q3_K_M.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-H-8B-Reasoning-128K-GGUF/blob/main/nvidia_Nemotron-H-8B-Reasoning-128K-Q3_K_M.gguf) | Q3_K_M | 4.03GB | false | Low quality. | +| [Nemotron-H-8B-Reasoning-128K-IQ3_M.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-H-8B-Reasoning-128K-GGUF/blob/main/nvidia_Nemotron-H-8B-Reasoning-128K-IQ3_M.gguf) | IQ3_M | 3.79GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [Nemotron-H-8B-Reasoning-128K-Q3_K_S.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-H-8B-Reasoning-128K-GGUF/blob/main/nvidia_Nemotron-H-8B-Reasoning-128K-Q3_K_S.gguf) | Q3_K_S | 3.70GB | false | Low quality, not recommended. | +| [Nemotron-H-8B-Reasoning-128K-Q2_K_L.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-H-8B-Reasoning-128K-GGUF/blob/main/nvidia_Nemotron-H-8B-Reasoning-128K-Q2_K_L.gguf) | Q2_K_L | 3.68GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [Nemotron-H-8B-Reasoning-128K-IQ3_XS.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-H-8B-Reasoning-128K-GGUF/blob/main/nvidia_Nemotron-H-8B-Reasoning-128K-IQ3_XS.gguf) | IQ3_XS | 3.63GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [Nemotron-H-8B-Reasoning-128K-IQ3_XXS.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-H-8B-Reasoning-128K-GGUF/blob/main/nvidia_Nemotron-H-8B-Reasoning-128K-IQ3_XXS.gguf) | IQ3_XXS | 3.30GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [Nemotron-H-8B-Reasoning-128K-Q2_K.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-H-8B-Reasoning-128K-GGUF/blob/main/nvidia_Nemotron-H-8B-Reasoning-128K-Q2_K.gguf) | Q2_K | 3.16GB | false | Very low quality but surprisingly usable. | +| [Nemotron-H-8B-Reasoning-128K-IQ2_M.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-H-8B-Reasoning-128K-GGUF/blob/main/nvidia_Nemotron-H-8B-Reasoning-128K-IQ2_M.gguf) | IQ2_M | 2.93GB | 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 + +
+ Click to view download instructions + +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-H-8B-Reasoning-128K-GGUF --include "nvidia_Nemotron-H-8B-Reasoning-128K-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-H-8B-Reasoning-128K-GGUF --include "nvidia_Nemotron-H-8B-Reasoning-128K-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (nvidia_Nemotron-H-8B-Reasoning-128K-Q8_0) or download them all in place (./) + +
+ +## 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. + +
+ Click to view Q4_0_X_X information (deprecated + +I'm keeping this section to show the potential theoretical uplift in performance from using the Q4_0 with online repacking. + +
+ Click to view benchmarks on an AVX2 system (EPYC7702) + +| 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 + +
+ +
+ +## Which file should I choose? + +
+ Click here for details + +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. + +
+ +## 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 diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/nvidia_Nemotron-H-8B-Reasoning-128K-IQ2_M.gguf b/nvidia_Nemotron-H-8B-Reasoning-128K-IQ2_M.gguf new file mode 100644 index 0000000..a3721e9 --- /dev/null +++ b/nvidia_Nemotron-H-8B-Reasoning-128K-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e4d891f321ea4847417f6e86c46d68bc4dd169353e3190a46c196d0edb279dc +size 2931592160 diff --git a/nvidia_Nemotron-H-8B-Reasoning-128K-IQ3_M.gguf b/nvidia_Nemotron-H-8B-Reasoning-128K-IQ3_M.gguf new file mode 100644 index 0000000..422501a --- /dev/null +++ b/nvidia_Nemotron-H-8B-Reasoning-128K-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3948900993e7c1a0f46c85fe2fb0a000a37a35a634de065c5be0d4cfb533751d +size 3785657312 diff --git a/nvidia_Nemotron-H-8B-Reasoning-128K-IQ3_XS.gguf b/nvidia_Nemotron-H-8B-Reasoning-128K-IQ3_XS.gguf new file mode 100644 index 0000000..c680d3e --- /dev/null +++ b/nvidia_Nemotron-H-8B-Reasoning-128K-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca0beba7afc34067b37972a2b685988cfa0dfeb399b3b44c1f510a419973c19d +size 3626077152 diff --git a/nvidia_Nemotron-H-8B-Reasoning-128K-IQ3_XXS.gguf b/nvidia_Nemotron-H-8B-Reasoning-128K-IQ3_XXS.gguf new file mode 100644 index 0000000..7a51b14 --- /dev/null +++ b/nvidia_Nemotron-H-8B-Reasoning-128K-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec77bab87061b7812ecf2d46562ac16ba645f92524bec7d790da6e22acb78a5a +size 3301608416 diff --git a/nvidia_Nemotron-H-8B-Reasoning-128K-IQ4_NL.gguf b/nvidia_Nemotron-H-8B-Reasoning-128K-IQ4_NL.gguf new file mode 100644 index 0000000..7268a84 --- /dev/null +++ b/nvidia_Nemotron-H-8B-Reasoning-128K-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a83df883ad44b5b747f856cdb381479ecc69c59fc94eb25fda240880fa77382e +size 4708699104 diff --git a/nvidia_Nemotron-H-8B-Reasoning-128K-IQ4_XS.gguf b/nvidia_Nemotron-H-8B-Reasoning-128K-IQ4_XS.gguf new file mode 100644 index 0000000..8ef8751 --- /dev/null +++ b/nvidia_Nemotron-H-8B-Reasoning-128K-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dc3d83c2b3ba991b474af1fdc588e0d19109da249baacfb6d1a0814221e2e36 +size 4472376288 diff --git a/nvidia_Nemotron-H-8B-Reasoning-128K-Q2_K.gguf b/nvidia_Nemotron-H-8B-Reasoning-128K-Q2_K.gguf new file mode 100644 index 0000000..cd2d934 --- /dev/null +++ b/nvidia_Nemotron-H-8B-Reasoning-128K-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcd51eba859f78de0544405cdf8d2ce67aa8fb106effbfdb829d7888065c6edd +size 3159493600 diff --git a/nvidia_Nemotron-H-8B-Reasoning-128K-Q2_K_L.gguf b/nvidia_Nemotron-H-8B-Reasoning-128K-Q2_K_L.gguf new file mode 100644 index 0000000..47d7651 --- /dev/null +++ b/nvidia_Nemotron-H-8B-Reasoning-128K-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfdfc45a684b97edb88b8bac7f95d0aff1b54f8937ba4e08b9154c0d48027a6a +size 3683781600 diff --git a/nvidia_Nemotron-H-8B-Reasoning-128K-Q3_K_L.gguf b/nvidia_Nemotron-H-8B-Reasoning-128K-Q3_K_L.gguf new file mode 100644 index 0000000..558a923 --- /dev/null +++ b/nvidia_Nemotron-H-8B-Reasoning-128K-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:624cd0b23892be47d5d22a5aaee5640d2ac361dd3c06be151d6aea34bee89390 +size 4270951392 diff --git a/nvidia_Nemotron-H-8B-Reasoning-128K-Q3_K_M.gguf b/nvidia_Nemotron-H-8B-Reasoning-128K-Q3_K_M.gguf new file mode 100644 index 0000000..ea95cb1 --- /dev/null +++ b/nvidia_Nemotron-H-8B-Reasoning-128K-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f32a39e8e797fde71f1bf394516a8765935cb7ca3d0f89358c4b92e8ed700b72 +size 4030303200 diff --git a/nvidia_Nemotron-H-8B-Reasoning-128K-Q3_K_S.gguf b/nvidia_Nemotron-H-8B-Reasoning-128K-Q3_K_S.gguf new file mode 100644 index 0000000..04bcdc2 --- /dev/null +++ b/nvidia_Nemotron-H-8B-Reasoning-128K-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4e3b9fd85b5f542c4f675b450da54ce324a3c35b0c0adb27dd61286392740fb +size 3704327136 diff --git a/nvidia_Nemotron-H-8B-Reasoning-128K-Q3_K_XL.gguf b/nvidia_Nemotron-H-8B-Reasoning-128K-Q3_K_XL.gguf new file mode 100644 index 0000000..11e7fa7 --- /dev/null +++ b/nvidia_Nemotron-H-8B-Reasoning-128K-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c316a334c946e575f8b081436ccec5258ca84d0c5e9971250f7afe8ad98b2fd9 +size 4740713440 diff --git a/nvidia_Nemotron-H-8B-Reasoning-128K-Q4_0.gguf b/nvidia_Nemotron-H-8B-Reasoning-128K-Q4_0.gguf new file mode 100644 index 0000000..fd3038f --- /dev/null +++ b/nvidia_Nemotron-H-8B-Reasoning-128K-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd1c37f82fe3ab8c753585742b960ad8c57c50b026c2e0604a9a4e1bc3ff71be +size 4741729248 diff --git a/nvidia_Nemotron-H-8B-Reasoning-128K-Q4_1.gguf b/nvidia_Nemotron-H-8B-Reasoning-128K-Q4_1.gguf new file mode 100644 index 0000000..603d7d2 --- /dev/null +++ b/nvidia_Nemotron-H-8B-Reasoning-128K-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfdbd5306f34f8025b50985bc72c851099568a65d6b30b2ca7f3688da48c1978 +size 5181344736 diff --git a/nvidia_Nemotron-H-8B-Reasoning-128K-Q4_K_L.gguf b/nvidia_Nemotron-H-8B-Reasoning-128K-Q4_K_L.gguf new file mode 100644 index 0000000..b6aa8b2 --- /dev/null +++ b/nvidia_Nemotron-H-8B-Reasoning-128K-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37a5a0573eef45fa43f91cf8632d479c25cacb800d9e1c356fc72e52085efd66 +size 5381819360 diff --git a/nvidia_Nemotron-H-8B-Reasoning-128K-Q4_K_M.gguf b/nvidia_Nemotron-H-8B-Reasoning-128K-Q4_K_M.gguf new file mode 100644 index 0000000..d8f91e0 --- /dev/null +++ b/nvidia_Nemotron-H-8B-Reasoning-128K-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:312ebd50999058707868f49011d87225fcc92af0f5a526cd3553f821dc161956 +size 4983360480 diff --git a/nvidia_Nemotron-H-8B-Reasoning-128K-Q4_K_S.gguf b/nvidia_Nemotron-H-8B-Reasoning-128K-Q4_K_S.gguf new file mode 100644 index 0000000..1f090f5 --- /dev/null +++ b/nvidia_Nemotron-H-8B-Reasoning-128K-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0968c2b1a90e4ad35c0b68ad3991f634c807eb10a3da5d15942516e2877eedd3 +size 4776856544 diff --git a/nvidia_Nemotron-H-8B-Reasoning-128K-Q5_K_L.gguf b/nvidia_Nemotron-H-8B-Reasoning-128K-Q5_K_L.gguf new file mode 100644 index 0000000..bb6bb1a --- /dev/null +++ b/nvidia_Nemotron-H-8B-Reasoning-128K-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:976b10ec96e6bccf40320731adbebc7e472293cfdb6bdf9d1f4efc3a3009a749 +size 6126832608 diff --git a/nvidia_Nemotron-H-8B-Reasoning-128K-Q5_K_M.gguf b/nvidia_Nemotron-H-8B-Reasoning-128K-Q5_K_M.gguf new file mode 100644 index 0000000..ef29f71 --- /dev/null +++ b/nvidia_Nemotron-H-8B-Reasoning-128K-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2624f499b97e138cb272823212183c2219a8537a295ba737d2d0cc09142f7453 +size 5795482592 diff --git a/nvidia_Nemotron-H-8B-Reasoning-128K-Q5_K_S.gguf b/nvidia_Nemotron-H-8B-Reasoning-128K-Q5_K_S.gguf new file mode 100644 index 0000000..3cb77d2 --- /dev/null +++ b/nvidia_Nemotron-H-8B-Reasoning-128K-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a6f16d1adbf3a0b73d95e2be14dd0899a54a64b28815bf61b02ba6c78e6a096 +size 5653990368 diff --git a/nvidia_Nemotron-H-8B-Reasoning-128K-Q6_K.gguf b/nvidia_Nemotron-H-8B-Reasoning-128K-Q6_K.gguf new file mode 100644 index 0000000..7993069 --- /dev/null +++ b/nvidia_Nemotron-H-8B-Reasoning-128K-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95c71afeac191b8cda9d84954578fd6d892fa42cf5b2bc3ea07caf4b3698d506 +size 6658362336 diff --git a/nvidia_Nemotron-H-8B-Reasoning-128K-Q6_K_L.gguf b/nvidia_Nemotron-H-8B-Reasoning-128K-Q6_K_L.gguf new file mode 100644 index 0000000..cca9ba4 --- /dev/null +++ b/nvidia_Nemotron-H-8B-Reasoning-128K-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f0996edc6ed1b5f43a8524ad1d8cfaaf31f05c566dd3fb04b50475e7420b277 +size 6918409184 diff --git a/nvidia_Nemotron-H-8B-Reasoning-128K-Q8_0.gguf b/nvidia_Nemotron-H-8B-Reasoning-128K-Q8_0.gguf new file mode 100644 index 0000000..9a3b6c5 --- /dev/null +++ b/nvidia_Nemotron-H-8B-Reasoning-128K-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9b1a4593565561275d6438ce4a3a0c455369aa3d7abecffcc8e3d0b7ecd0fe6 +size 8619887584 diff --git a/nvidia_Nemotron-H-8B-Reasoning-128K-bf16.gguf b/nvidia_Nemotron-H-8B-Reasoning-128K-bf16.gguf new file mode 100644 index 0000000..40d1945 --- /dev/null +++ b/nvidia_Nemotron-H-8B-Reasoning-128K-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73a43da226bf9502584260661ed466ec8c3b97f712db4d70a968e7b35279be77 +size 16212888224 diff --git a/nvidia_Nemotron-H-8B-Reasoning-128K-imatrix.gguf b/nvidia_Nemotron-H-8B-Reasoning-128K-imatrix.gguf new file mode 100644 index 0000000..f35364d --- /dev/null +++ b/nvidia_Nemotron-H-8B-Reasoning-128K-imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b349909b4a869195f75fea420a3a3344a5efde64407ffa410245c2d535b09a3 +size 3916672