commit 969fcb37c2992da043cd308025b7e4abb95aced0 Author: ModelHub XC Date: Tue Jul 21 19:45:06 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/ibm-granite_granite-4.0-h-tiny-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9792398 --- /dev/null +++ b/.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 + +ibm-granite_granite-4.0-h-tiny-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-h-tiny-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-h-tiny-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-h-tiny-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-h-tiny-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-h-tiny-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-h-tiny-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-h-tiny-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-h-tiny-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-h-tiny-bf16.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-h-tiny-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-h-tiny-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-h-tiny-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-h-tiny-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-h-tiny-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-h-tiny-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-h-tiny-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-h-tiny-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-h-tiny-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-h-tiny-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-h-tiny-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-h-tiny-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-h-tiny-imatrix.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-h-tiny-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-h-tiny-IQ3_XS.gguf 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..665c065 --- /dev/null +++ b/README.md @@ -0,0 +1,164 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +base_model_relation: quantized +base_model: ibm-granite/granite-4.0-h-tiny +--- + +## Llamacpp imatrix Quantizations of granite-4.0-h-tiny by ibm-granite + +Using llama.cpp release b6647 for quantization. + +Original model: https://huggingface.co/ibm-granite/granite-4.0-h-tiny + +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 | +| -------- | ---------- | --------- | ----- | ----------- | +| [granite-4.0-h-tiny-bf16.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-bf16.gguf) | bf16 | 13.89GB | false | Full BF16 weights. | +| [granite-4.0-h-tiny-Q8_0.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-Q8_0.gguf) | Q8_0 | 7.39GB | false | Extremely high quality, generally unneeded but max available quant. | +| [granite-4.0-h-tiny-Q6_K_L.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-Q6_K_L.gguf) | Q6_K_L | 5.79GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [granite-4.0-h-tiny-Q6_K.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-Q6_K.gguf) | Q6_K | 5.76GB | false | Very high quality, near perfect, *recommended*. | +| [granite-4.0-h-tiny-Q5_K_L.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-Q5_K_L.gguf) | Q5_K_L | 5.05GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [granite-4.0-h-tiny-Q5_K_M.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-Q5_K_M.gguf) | Q5_K_M | 5.02GB | false | High quality, *recommended*. | +| [granite-4.0-h-tiny-Q5_K_S.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-Q5_K_S.gguf) | Q5_K_S | 4.86GB | false | High quality, *recommended*. | +| [granite-4.0-h-tiny-Q4_1.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-Q4_1.gguf) | Q4_1 | 4.44GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [granite-4.0-h-tiny-Q4_K_L.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-Q4_K_L.gguf) | Q4_K_L | 4.33GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [granite-4.0-h-tiny-Q4_K_M.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-Q4_K_M.gguf) | Q4_K_M | 4.30GB | false | Good quality, default size for most use cases, *recommended*. | +| [granite-4.0-h-tiny-Q4_K_S.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-Q4_K_S.gguf) | Q4_K_S | 4.15GB | false | Slightly lower quality with more space savings, *recommended*. | +| [granite-4.0-h-tiny-Q4_0.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-Q4_0.gguf) | Q4_0 | 4.09GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [granite-4.0-h-tiny-IQ4_NL.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-IQ4_NL.gguf) | IQ4_NL | 4.02GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [granite-4.0-h-tiny-IQ4_XS.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-IQ4_XS.gguf) | IQ4_XS | 3.82GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [granite-4.0-h-tiny-Q3_K_XL.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-Q3_K_XL.gguf) | Q3_K_XL | 3.45GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [granite-4.0-h-tiny-Q3_K_L.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-Q3_K_L.gguf) | Q3_K_L | 3.41GB | false | Lower quality but usable, good for low RAM availability. | +| [granite-4.0-h-tiny-Q3_K_M.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-Q3_K_M.gguf) | Q3_K_M | 3.29GB | false | Low quality. | +| [granite-4.0-h-tiny-IQ3_M.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-IQ3_M.gguf) | IQ3_M | 3.29GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [granite-4.0-h-tiny-Q3_K_S.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-Q3_K_S.gguf) | Q3_K_S | 3.15GB | false | Low quality, not recommended. | +| [granite-4.0-h-tiny-IQ3_XS.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-IQ3_XS.gguf) | IQ3_XS | 3.01GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [granite-4.0-h-tiny-IQ3_XXS.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-IQ3_XXS.gguf) | IQ3_XXS | 2.87GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [granite-4.0-h-tiny-Q2_K_L.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-Q2_K_L.gguf) | Q2_K_L | 2.62GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [granite-4.0-h-tiny-Q2_K.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-Q2_K.gguf) | Q2_K | 2.59GB | false | Very low quality but surprisingly usable. | +| [granite-4.0-h-tiny-IQ2_M.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-IQ2_M.gguf) | IQ2_M | 2.29GB | 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/ibm-granite_granite-4.0-h-tiny-GGUF --include "ibm-granite_granite-4.0-h-tiny-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/ibm-granite_granite-4.0-h-tiny-GGUF --include "ibm-granite_granite-4.0-h-tiny-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (ibm-granite_granite-4.0-h-tiny-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/ibm-granite_granite-4.0-h-tiny-IQ2_M.gguf b/ibm-granite_granite-4.0-h-tiny-IQ2_M.gguf new file mode 100644 index 0000000..101c64a --- /dev/null +++ b/ibm-granite_granite-4.0-h-tiny-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06f75822f83db56e9b66dd46ec7c845f68312df10259f33bce56d2d83527d9d8 +size 2291237952 diff --git a/ibm-granite_granite-4.0-h-tiny-IQ3_M.gguf b/ibm-granite_granite-4.0-h-tiny-IQ3_M.gguf new file mode 100644 index 0000000..5b54b1b --- /dev/null +++ b/ibm-granite_granite-4.0-h-tiny-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49f6587da93654c50f6c3c6d572fe380363c279fd840f1b49e3cdae3b7a892a7 +size 3285037632 diff --git a/ibm-granite_granite-4.0-h-tiny-IQ3_XS.gguf b/ibm-granite_granite-4.0-h-tiny-IQ3_XS.gguf new file mode 100644 index 0000000..228aae5 --- /dev/null +++ b/ibm-granite_granite-4.0-h-tiny-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:408595ac18fea857a2398ba135738883262ef837ce0ce610a313838b508e33c9 +size 3008926272 diff --git a/ibm-granite_granite-4.0-h-tiny-IQ3_XXS.gguf b/ibm-granite_granite-4.0-h-tiny-IQ3_XXS.gguf new file mode 100644 index 0000000..c8e9d59 --- /dev/null +++ b/ibm-granite_granite-4.0-h-tiny-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3429ad758378097a5173e78ec1bc5cc81611a33c1ec571d87862af1f8b4351b9 +size 2868669504 diff --git a/ibm-granite_granite-4.0-h-tiny-IQ4_NL.gguf b/ibm-granite_granite-4.0-h-tiny-IQ4_NL.gguf new file mode 100644 index 0000000..2a387cc --- /dev/null +++ b/ibm-granite_granite-4.0-h-tiny-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4257dd9c4f20bbe64bccc9643b479a9bfba91e5a0c74b752868c916a7f4042db +size 4024673088 diff --git a/ibm-granite_granite-4.0-h-tiny-IQ4_XS.gguf b/ibm-granite_granite-4.0-h-tiny-IQ4_XS.gguf new file mode 100644 index 0000000..d5bdd75 --- /dev/null +++ b/ibm-granite_granite-4.0-h-tiny-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:761bf97b24d7386f4f814f92ad53bba55aaad1b612b4a1023d604d1358cc353c +size 3819085632 diff --git a/ibm-granite_granite-4.0-h-tiny-Q2_K.gguf b/ibm-granite_granite-4.0-h-tiny-Q2_K.gguf new file mode 100644 index 0000000..0a26372 --- /dev/null +++ b/ibm-granite_granite-4.0-h-tiny-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:873f7d981dea6555f855759559e963ed73d04a1cd9b98cb9f799da2d5addf1eb +size 2585322816 diff --git a/ibm-granite_granite-4.0-h-tiny-Q2_K_L.gguf b/ibm-granite_granite-4.0-h-tiny-Q2_K_L.gguf new file mode 100644 index 0000000..34a2a5a --- /dev/null +++ b/ibm-granite_granite-4.0-h-tiny-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:643663be82267e81a17e2aefb9e84515751fccb476e21a799821f8d2c08dc91a +size 2622653760 diff --git a/ibm-granite_granite-4.0-h-tiny-Q3_K_L.gguf b/ibm-granite_granite-4.0-h-tiny-Q3_K_L.gguf new file mode 100644 index 0000000..8282858 --- /dev/null +++ b/ibm-granite_granite-4.0-h-tiny-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7884ea5ca8d834782c5ce12eac5c082d42df6ee088f1e97e7bf86e1e60829c9d +size 3408826944 diff --git a/ibm-granite_granite-4.0-h-tiny-Q3_K_M.gguf b/ibm-granite_granite-4.0-h-tiny-Q3_K_M.gguf new file mode 100644 index 0000000..a9733aa --- /dev/null +++ b/ibm-granite_granite-4.0-h-tiny-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cb3b2e61565c811c183a3ad3f5398703feca907c1ef30f8c77ad6c54b62756b +size 3285234240 diff --git a/ibm-granite_granite-4.0-h-tiny-Q3_K_S.gguf b/ibm-granite_granite-4.0-h-tiny-Q3_K_S.gguf new file mode 100644 index 0000000..61fe26e --- /dev/null +++ b/ibm-granite_granite-4.0-h-tiny-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd89fd0214f4730405084afd43efd5652f8e62d20d52b821024a0a9f6b07af2e +size 3150926400 diff --git a/ibm-granite_granite-4.0-h-tiny-Q3_K_XL.gguf b/ibm-granite_granite-4.0-h-tiny-Q3_K_XL.gguf new file mode 100644 index 0000000..c4a0824 --- /dev/null +++ b/ibm-granite_granite-4.0-h-tiny-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dae381645f8c956cdf52325c936c37084c64e145c44e9902ac59953411b5745 +size 3446157888 diff --git a/ibm-granite_granite-4.0-h-tiny-Q4_0.gguf b/ibm-granite_granite-4.0-h-tiny-Q4_0.gguf new file mode 100644 index 0000000..e6030fb --- /dev/null +++ b/ibm-granite_granite-4.0-h-tiny-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30eae42251c8b8c9d87326351255b55c6a328c492224dd7a28120bf064a28819 +size 4086408000 diff --git a/ibm-granite_granite-4.0-h-tiny-Q4_1.gguf b/ibm-granite_granite-4.0-h-tiny-Q4_1.gguf new file mode 100644 index 0000000..2e0b446 --- /dev/null +++ b/ibm-granite_granite-4.0-h-tiny-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7190245c2ef70aa9ec84daceb94b4263a096127086798a69d34f55b9c496ad17 +size 4435258176 diff --git a/ibm-granite_granite-4.0-h-tiny-Q4_K_L.gguf b/ibm-granite_granite-4.0-h-tiny-Q4_K_L.gguf new file mode 100644 index 0000000..0a28c7d --- /dev/null +++ b/ibm-granite_granite-4.0-h-tiny-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82484a50c20e6b3072a7ed4d270f0198990bade447699ab45c344beeab4e600f +size 4334465856 diff --git a/ibm-granite_granite-4.0-h-tiny-Q4_K_M.gguf b/ibm-granite_granite-4.0-h-tiny-Q4_K_M.gguf new file mode 100644 index 0000000..bfd8f55 --- /dev/null +++ b/ibm-granite_granite-4.0-h-tiny-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33a689fe7f35b14ebab3ae599b65aaa3ed8548c393373b1b0eebee36c653146f +size 4297134912 diff --git a/ibm-granite_granite-4.0-h-tiny-Q4_K_S.gguf b/ibm-granite_granite-4.0-h-tiny-Q4_K_S.gguf new file mode 100644 index 0000000..7bb170b --- /dev/null +++ b/ibm-granite_granite-4.0-h-tiny-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:571e43f86e3316a14af523e566fef5d48e8377803a9c44ace8af26cc88926d0a +size 4150895424 diff --git a/ibm-granite_granite-4.0-h-tiny-Q5_K_L.gguf b/ibm-granite_granite-4.0-h-tiny-Q5_K_L.gguf new file mode 100644 index 0000000..4c40999 --- /dev/null +++ b/ibm-granite_granite-4.0-h-tiny-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb3de6a22235772243d799b6f45262c1fe104a5f0561fb1364999954fc5ddf16 +size 5053645632 diff --git a/ibm-granite_granite-4.0-h-tiny-Q5_K_M.gguf b/ibm-granite_granite-4.0-h-tiny-Q5_K_M.gguf new file mode 100644 index 0000000..4d786d2 --- /dev/null +++ b/ibm-granite_granite-4.0-h-tiny-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbf86daa13091ed5591b341d74b751f47b23242546998f62cf97d8355db4a70a +size 5016314688 diff --git a/ibm-granite_granite-4.0-h-tiny-Q5_K_S.gguf b/ibm-granite_granite-4.0-h-tiny-Q5_K_S.gguf new file mode 100644 index 0000000..1107aff --- /dev/null +++ b/ibm-granite_granite-4.0-h-tiny-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d915a1bccc4129d4d54a789562790b4f30933951e13c528afe14fa2917e84b0b +size 4859556672 diff --git a/ibm-granite_granite-4.0-h-tiny-Q6_K.gguf b/ibm-granite_granite-4.0-h-tiny-Q6_K.gguf new file mode 100644 index 0000000..9731256 --- /dev/null +++ b/ibm-granite_granite-4.0-h-tiny-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c1c57e35d687b7ce24eb283c89d2ca7e2cf598d05521800329a8d62ce9e45ca +size 5757412416 diff --git a/ibm-granite_granite-4.0-h-tiny-Q6_K_L.gguf b/ibm-granite_granite-4.0-h-tiny-Q6_K_L.gguf new file mode 100644 index 0000000..0e5c25d --- /dev/null +++ b/ibm-granite_granite-4.0-h-tiny-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:156529c8f187a1405c1d766694c98faf4e022ef441d688840ef0a5a5ab6db097 +size 5794743360 diff --git a/ibm-granite_granite-4.0-h-tiny-Q8_0.gguf b/ibm-granite_granite-4.0-h-tiny-Q8_0.gguf new file mode 100644 index 0000000..2de0ea6 --- /dev/null +++ b/ibm-granite_granite-4.0-h-tiny-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa3799edad3bf487827a298f1cfbc26269ca4ee6fe87706efe76120a107d6787 +size 7390331712 diff --git a/ibm-granite_granite-4.0-h-tiny-bf16.gguf b/ibm-granite_granite-4.0-h-tiny-bf16.gguf new file mode 100644 index 0000000..f7ebd75 --- /dev/null +++ b/ibm-granite_granite-4.0-h-tiny-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3158f000b5991e49bca070457b354d5981bfd27dca68e536516a9e0fdeb76c99 +size 13891205952 diff --git a/ibm-granite_granite-4.0-h-tiny-imatrix.gguf b/ibm-granite_granite-4.0-h-tiny-imatrix.gguf new file mode 100644 index 0000000..c844cee --- /dev/null +++ b/ibm-granite_granite-4.0-h-tiny-imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:309bc231f05cc5bf2c01478b31a69ad565767b89637714876e0ec2792211b66a +size 38451424