commit f6c06eecfe78708514ea938d74357416468ce266 Author: ModelHub XC Date: Sun Aug 16 07:09:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/google_gemma-3-4b-it-qat-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..530b671 --- /dev/null +++ b/README.md @@ -0,0 +1,189 @@ +--- +quantized_by: bartowski +pipeline_tag: image-text-to-text +tags: +- gemma3 +- gemma +- google +license: gemma +extra_gated_button_content: Acknowledge license +base_model_relation: quantized +extra_gated_heading: Access Gemma on Hugging Face +extra_gated_prompt: >- + To access Gemma on Hugging Face, you’re required to review and agree to + Google’s usage license. To do this, please ensure you’re logged in to Hugging + Face and click below. Requests are processed immediately. +base_model: google/gemma-3-4b-it-qat-q4_0-unquantized +--- + +## Llamacpp imatrix Quantizations of gemma-3-4b-it-qat by google + +These are derived from the QAT (quantized aware training) weights provided by Google + +*ONLY* Q4_0 is expected to be better, but figured while I'm at it I might as well make others to see what happens? + +[gemma-3-4b-it-qat-Q4_0.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-Q4_0.gguf) | Q4_0 | 2.37GB | false | Should be improved due to QAT, offers online repacking for ARM and AVX CPU inference. + +Using llama.cpp release b5147 for quantization. + +Original model: https://huggingface.co/google/gemma-3-4b-it-qat-q4_0-unquantized + +All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8) + +Run them in [LM Studio](https://lmstudio.ai/) + +Run them directly with [llama.cpp](https://github.com/ggerganov/llama.cpp), or any other llama.cpp based project + +## Prompt format + +``` +user +{system_prompt} + +{prompt} +model + +model +``` + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [gemma-3-4b-it-qat-bf16.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-bf16.gguf) | bf16 | 7.77GB | false | Full BF16 weights. | +| [gemma-3-4b-it-qat-Q8_0.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-Q8_0.gguf) | Q8_0 | 4.13GB | false | Extremely high quality, generally unneeded but max available quant. | +| [gemma-3-4b-it-qat-Q6_K_L.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-Q6_K_L.gguf) | Q6_K_L | 3.35GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [gemma-3-4b-it-qat-Q6_K.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-Q6_K.gguf) | Q6_K | 3.19GB | false | Very high quality, near perfect, *recommended*. | +| [gemma-3-4b-it-qat-Q5_K_L.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-Q5_K_L.gguf) | Q5_K_L | 2.99GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [gemma-3-4b-it-qat-Q5_K_M.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-Q5_K_M.gguf) | Q5_K_M | 2.83GB | false | High quality, *recommended*. | +| [gemma-3-4b-it-qat-Q5_K_S.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-Q5_K_S.gguf) | Q5_K_S | 2.76GB | false | High quality, *recommended*. | +| [gemma-3-4b-it-qat-Q4_K_L.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-Q4_K_L.gguf) | Q4_K_L | 2.65GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [gemma-3-4b-it-qat-Q4_1.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-Q4_1.gguf) | Q4_1 | 2.56GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [gemma-3-4b-it-qat-Q4_K_M.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-Q4_K_M.gguf) | Q4_K_M | 2.49GB | false | Good quality, default size for most use cases, *recommended*. | +| [gemma-3-4b-it-qat-Q3_K_XL.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-Q3_K_XL.gguf) | Q3_K_XL | 2.40GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [gemma-3-4b-it-qat-Q4_K_S.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-Q4_K_S.gguf) | Q4_K_S | 2.38GB | false | Slightly lower quality with more space savings, *recommended*. | +| [gemma-3-4b-it-qat-Q4_0.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-Q4_0.gguf) | Q4_0 | 2.37GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [gemma-3-4b-it-qat-IQ4_NL.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-IQ4_NL.gguf) | IQ4_NL | 2.36GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [gemma-3-4b-it-qat-IQ4_XS.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-IQ4_XS.gguf) | IQ4_XS | 2.26GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [gemma-3-4b-it-qat-Q3_K_L.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-Q3_K_L.gguf) | Q3_K_L | 2.24GB | false | Lower quality but usable, good for low RAM availability. | +| [gemma-3-4b-it-qat-Q3_K_M.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-Q3_K_M.gguf) | Q3_K_M | 2.10GB | false | Low quality. | +| [gemma-3-4b-it-qat-IQ3_M.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-IQ3_M.gguf) | IQ3_M | 1.99GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [gemma-3-4b-it-qat-Q3_K_S.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-Q3_K_S.gguf) | Q3_K_S | 1.94GB | false | Low quality, not recommended. | +| [gemma-3-4b-it-qat-Q2_K_L.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-Q2_K_L.gguf) | Q2_K_L | 1.89GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [gemma-3-4b-it-qat-IQ3_XS.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-IQ3_XS.gguf) | IQ3_XS | 1.86GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [gemma-3-4b-it-qat-Q2_K.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-Q2_K.gguf) | Q2_K | 1.73GB | false | Very low quality but surprisingly usable. | +| [gemma-3-4b-it-qat-IQ3_XXS.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-IQ3_XXS.gguf) | IQ3_XXS | 1.69GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [gemma-3-4b-it-qat-IQ2_M.gguf](https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF/blob/main/google_gemma-3-4b-it-qat-IQ2_M.gguf) | IQ2_M | 1.54GB | 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/google_gemma-3-4b-it-qat-GGUF --include "google_gemma-3-4b-it-qat-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/google_gemma-3-4b-it-qat-GGUF --include "google_gemma-3-4b-it-qat-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (google_gemma-3-4b-it-qat-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/ggerganov/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/ggerganov/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/ggerganov/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/ggerganov/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 \ No newline at end of file diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..4aef15d --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "image-text-to-text", "allow_remote": true} \ No newline at end of file diff --git a/google_gemma-3-4b-it-qat-IQ2_M.gguf b/google_gemma-3-4b-it-qat-IQ2_M.gguf new file mode 100644 index 0000000..3a326c8 --- /dev/null +++ b/google_gemma-3-4b-it-qat-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c2b1894f89c82501adde440286834dbaf75f77971785a18a643bf7ed444b341 +size 1537982624 diff --git a/google_gemma-3-4b-it-qat-IQ3_M.gguf b/google_gemma-3-4b-it-qat-IQ3_M.gguf new file mode 100644 index 0000000..c9772dc --- /dev/null +++ b/google_gemma-3-4b-it-qat-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65d2890dc1c82aff8ff1820aa3acb5293218f5dd6a88f79efd686d8e700f5839 +size 1986803104 diff --git a/google_gemma-3-4b-it-qat-IQ3_XS.gguf b/google_gemma-3-4b-it-qat-IQ3_XS.gguf new file mode 100644 index 0000000..2fa522f --- /dev/null +++ b/google_gemma-3-4b-it-qat-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2976c0abcc70aad7dc4c1524fcc31add527206f52dca60eeab546a420477ea95 +size 1863390624 diff --git a/google_gemma-3-4b-it-qat-IQ3_XXS.gguf b/google_gemma-3-4b-it-qat-IQ3_XXS.gguf new file mode 100644 index 0000000..3d25a02 --- /dev/null +++ b/google_gemma-3-4b-it-qat-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbb588cd5d068491bf02112881207437731dd23d0dd77a14d298e72d2df6baaf +size 1689452704 diff --git a/google_gemma-3-4b-it-qat-IQ4_NL.gguf b/google_gemma-3-4b-it-qat-IQ4_NL.gguf new file mode 100644 index 0000000..dac45e9 --- /dev/null +++ b/google_gemma-3-4b-it-qat-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:964e89d953e100a9ac67d1598cf07cb5f40aeabef73d9f1551df44a98700bf5b +size 2363512224 diff --git a/google_gemma-3-4b-it-qat-IQ4_XS.gguf b/google_gemma-3-4b-it-qat-IQ4_XS.gguf new file mode 100644 index 0000000..1a742a9 --- /dev/null +++ b/google_gemma-3-4b-it-qat-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4be7f6bacbef3df02216c3cefd65e07c926da9d8a43f335c9838aebc0e9f2454 +size 2263242144 diff --git a/google_gemma-3-4b-it-qat-Q2_K.gguf b/google_gemma-3-4b-it-qat-Q2_K.gguf new file mode 100644 index 0000000..920b9bc --- /dev/null +++ b/google_gemma-3-4b-it-qat-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1b967d515da3dd59cd1c9792c044b1b6bbb92d18416f3b3ce9c6dd38d49ed0e +size 1729164704 diff --git a/google_gemma-3-4b-it-qat-Q2_K_L.gguf b/google_gemma-3-4b-it-qat-Q2_K_L.gguf new file mode 100644 index 0000000..fc5c084 --- /dev/null +++ b/google_gemma-3-4b-it-qat-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb70394c826e4c0c43c54f0b2e4515ba05abbe01bdeedae9513ba8fdd2244545 +size 1891733664 diff --git a/google_gemma-3-4b-it-qat-Q3_K_L.gguf b/google_gemma-3-4b-it-qat-Q3_K_L.gguf new file mode 100644 index 0000000..ef1d3a9 --- /dev/null +++ b/google_gemma-3-4b-it-qat-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f04eec2665818d5a42ec92eef0aba8a406cc007149bfa1a8cd840a85d66b305 +size 2236085664 diff --git a/google_gemma-3-4b-it-qat-Q3_K_M.gguf b/google_gemma-3-4b-it-qat-Q3_K_M.gguf new file mode 100644 index 0000000..2dbc387 --- /dev/null +++ b/google_gemma-3-4b-it-qat-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d981cc6b6826ee6ba608d7756f4c27de9e2d075ffd364777aca53783f0d9356b +size 2098460064 diff --git a/google_gemma-3-4b-it-qat-Q3_K_S.gguf b/google_gemma-3-4b-it-qat-Q3_K_S.gguf new file mode 100644 index 0000000..4bd193f --- /dev/null +++ b/google_gemma-3-4b-it-qat-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f9d48a55d415f934645218354c0cc913ac7e666183432646bb535314d9fa739 +size 1937364384 diff --git a/google_gemma-3-4b-it-qat-Q3_K_XL.gguf b/google_gemma-3-4b-it-qat-Q3_K_XL.gguf new file mode 100644 index 0000000..de9686f --- /dev/null +++ b/google_gemma-3-4b-it-qat-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72f5466b84f8e340b0e45ec8160028b8252954c4e2ff4fa7d5d7757c9d5a3e60 +size 2398654624 diff --git a/google_gemma-3-4b-it-qat-Q4_0.gguf b/google_gemma-3-4b-it-qat-Q4_0.gguf new file mode 100644 index 0000000..66be08b --- /dev/null +++ b/google_gemma-3-4b-it-qat-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0231e2cba887f4c7834c39b34251e26b2eebbb71dfac0f7e6e2b2c2531c1a583 +size 2370065824 diff --git a/google_gemma-3-4b-it-qat-Q4_1.gguf b/google_gemma-3-4b-it-qat-Q4_1.gguf new file mode 100644 index 0000000..8c12093 --- /dev/null +++ b/google_gemma-3-4b-it-qat-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4d291a13da4e66fb9885911c12f823e3f56f11dbcbe961f4d87036c89cbdd54 +size 2564052384 diff --git a/google_gemma-3-4b-it-qat-Q4_K_L.gguf b/google_gemma-3-4b-it-qat-Q4_K_L.gguf new file mode 100644 index 0000000..866b9f3 --- /dev/null +++ b/google_gemma-3-4b-it-qat-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0dc9943512cd63de0d823db17d7ed0eb7bcd8009154a728cc70dbffca245358 +size 2652463264 diff --git a/google_gemma-3-4b-it-qat-Q4_K_M.gguf b/google_gemma-3-4b-it-qat-Q4_K_M.gguf new file mode 100644 index 0000000..7452ad2 --- /dev/null +++ b/google_gemma-3-4b-it-qat-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00165396c856791d12d935d8094b360c71243abd7475390d1efe4e109035b964 +size 2489894304 diff --git a/google_gemma-3-4b-it-qat-Q4_K_S.gguf b/google_gemma-3-4b-it-qat-Q4_K_S.gguf new file mode 100644 index 0000000..07e4f58 --- /dev/null +++ b/google_gemma-3-4b-it-qat-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc4b486f7bd4a1c3ac6237104ffd13b06f9d1d416f10bfac299e2638c71b0553 +size 2377930144 diff --git a/google_gemma-3-4b-it-qat-Q5_K_L.gguf b/google_gemma-3-4b-it-qat-Q5_K_L.gguf new file mode 100644 index 0000000..63acf8b --- /dev/null +++ b/google_gemma-3-4b-it-qat-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2409ae30a733a78385f82ad762f99b64016e975dfd8a62b2b91ad4515e330be +size 2992267424 diff --git a/google_gemma-3-4b-it-qat-Q5_K_M.gguf b/google_gemma-3-4b-it-qat-Q5_K_M.gguf new file mode 100644 index 0000000..74fd655 --- /dev/null +++ b/google_gemma-3-4b-it-qat-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca258aa4d97be94ac66d27e538552003af4c4bab1f596ef0469753d7f0f06c96 +size 2829698464 diff --git a/google_gemma-3-4b-it-qat-Q5_K_S.gguf b/google_gemma-3-4b-it-qat-Q5_K_S.gguf new file mode 100644 index 0000000..60042f8 --- /dev/null +++ b/google_gemma-3-4b-it-qat-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cad754df66c16a98a999dbb8ed32491d2c301c88fa7820b662e13f03293421f1 +size 2764592544 diff --git a/google_gemma-3-4b-it-qat-Q6_K.gguf b/google_gemma-3-4b-it-qat-Q6_K.gguf new file mode 100644 index 0000000..f2bb5a0 --- /dev/null +++ b/google_gemma-3-4b-it-qat-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7791f894e35f458f2add66f597e2ba62b477934978d6ca419a04df55ec6a4e47 +size 3190740384 diff --git a/google_gemma-3-4b-it-qat-Q6_K_L.gguf b/google_gemma-3-4b-it-qat-Q6_K_L.gguf new file mode 100644 index 0000000..236be96 --- /dev/null +++ b/google_gemma-3-4b-it-qat-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58fbabad0e07bdb27c310fbf6c8bde399855714e954d4feef75f2315c3690d76 +size 3353309344 diff --git a/google_gemma-3-4b-it-qat-Q8_0.gguf b/google_gemma-3-4b-it-qat-Q8_0.gguf new file mode 100644 index 0000000..92c609a --- /dev/null +++ b/google_gemma-3-4b-it-qat-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7165216f1d87c9c1cc4932afb24e99d8c348392c0dfbf4e9756c8b5eabf82a4f +size 4130402464 diff --git a/google_gemma-3-4b-it-qat-bf16.gguf b/google_gemma-3-4b-it-qat-bf16.gguf new file mode 100644 index 0000000..40d14d1 --- /dev/null +++ b/google_gemma-3-4b-it-qat-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c54dff5d89a4f05f83b4faebc75f4edb3ed2b5997a9eb20b07478dfab3cb8cb +size 7767803808 diff --git a/google_gemma-3-4b-it-qat.imatrix b/google_gemma-3-4b-it-qat.imatrix new file mode 100644 index 0000000..696d48c Binary files /dev/null and b/google_gemma-3-4b-it-qat.imatrix differ diff --git a/mmproj-google_gemma-3-4b-it-qat-f16.gguf b/mmproj-google_gemma-3-4b-it-qat-f16.gguf new file mode 100644 index 0000000..3be244e --- /dev/null +++ b/mmproj-google_gemma-3-4b-it-qat-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c0fb064b019a6972856aaae2c7e4792858af3ca4561be2dbf649123ba6c40cb +size 851251104