commit 29265a9180cc25197157956477988e775f4add66 Author: ModelHub XC Date: Thu Aug 6 23:42:14 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/TheDrummer_Fallen-Gemma3-4B-v1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4bc20a7 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,24 @@ +TheDrummer_Fallen-Gemma3-4B-v1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Fallen-Gemma3-4B-v1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Fallen-Gemma3-4B-v1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Fallen-Gemma3-4B-v1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Fallen-Gemma3-4B-v1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Fallen-Gemma3-4B-v1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Fallen-Gemma3-4B-v1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Fallen-Gemma3-4B-v1-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Fallen-Gemma3-4B-v1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Fallen-Gemma3-4B-v1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Fallen-Gemma3-4B-v1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Fallen-Gemma3-4B-v1-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Fallen-Gemma3-4B-v1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Fallen-Gemma3-4B-v1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Fallen-Gemma3-4B-v1-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Fallen-Gemma3-4B-v1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Fallen-Gemma3-4B-v1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Fallen-Gemma3-4B-v1-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Fallen-Gemma3-4B-v1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Fallen-Gemma3-4B-v1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Fallen-Gemma3-4B-v1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Fallen-Gemma3-4B-v1-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Fallen-Gemma3-4B-v1-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Fallen-Gemma3-4B-v1-bf16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..df8cfa8 --- /dev/null +++ b/README.md @@ -0,0 +1,173 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +license: other +base_model_relation: quantized +base_model: TheDrummer/Fallen-Gemma3-4B-v1 +--- + +## Llamacpp imatrix Quantizations of Fallen-Gemma3-4B-v1 by TheDrummer + +Using llama.cpp release b4925 for quantization. + +Original model: https://huggingface.co/TheDrummer/Fallen-Gemma3-4B-v1 + +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 | +| -------- | ---------- | --------- | ----- | ----------- | +| [Fallen-Gemma3-4B-v1-bf16.gguf](https://huggingface.co/bartowski/TheDrummer_Fallen-Gemma3-4B-v1-GGUF/blob/main/TheDrummer_Fallen-Gemma3-4B-v1-bf16.gguf) | bf16 | 7.77GB | false | Full BF16 weights. | +| [Fallen-Gemma3-4B-v1-Q8_0.gguf](https://huggingface.co/bartowski/TheDrummer_Fallen-Gemma3-4B-v1-GGUF/blob/main/TheDrummer_Fallen-Gemma3-4B-v1-Q8_0.gguf) | Q8_0 | 4.13GB | false | Extremely high quality, generally unneeded but max available quant. | +| [Fallen-Gemma3-4B-v1-Q6_K_L.gguf](https://huggingface.co/bartowski/TheDrummer_Fallen-Gemma3-4B-v1-GGUF/blob/main/TheDrummer_Fallen-Gemma3-4B-v1-Q6_K_L.gguf) | Q6_K_L | 3.35GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [Fallen-Gemma3-4B-v1-Q6_K.gguf](https://huggingface.co/bartowski/TheDrummer_Fallen-Gemma3-4B-v1-GGUF/blob/main/TheDrummer_Fallen-Gemma3-4B-v1-Q6_K.gguf) | Q6_K | 3.19GB | false | Very high quality, near perfect, *recommended*. | +| [Fallen-Gemma3-4B-v1-Q5_K_L.gguf](https://huggingface.co/bartowski/TheDrummer_Fallen-Gemma3-4B-v1-GGUF/blob/main/TheDrummer_Fallen-Gemma3-4B-v1-Q5_K_L.gguf) | Q5_K_L | 2.99GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [Fallen-Gemma3-4B-v1-Q5_K_M.gguf](https://huggingface.co/bartowski/TheDrummer_Fallen-Gemma3-4B-v1-GGUF/blob/main/TheDrummer_Fallen-Gemma3-4B-v1-Q5_K_M.gguf) | Q5_K_M | 2.83GB | false | High quality, *recommended*. | +| [Fallen-Gemma3-4B-v1-Q5_K_S.gguf](https://huggingface.co/bartowski/TheDrummer_Fallen-Gemma3-4B-v1-GGUF/blob/main/TheDrummer_Fallen-Gemma3-4B-v1-Q5_K_S.gguf) | Q5_K_S | 2.76GB | false | High quality, *recommended*. | +| [Fallen-Gemma3-4B-v1-Q4_K_L.gguf](https://huggingface.co/bartowski/TheDrummer_Fallen-Gemma3-4B-v1-GGUF/blob/main/TheDrummer_Fallen-Gemma3-4B-v1-Q4_K_L.gguf) | Q4_K_L | 2.65GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [Fallen-Gemma3-4B-v1-Q4_1.gguf](https://huggingface.co/bartowski/TheDrummer_Fallen-Gemma3-4B-v1-GGUF/blob/main/TheDrummer_Fallen-Gemma3-4B-v1-Q4_1.gguf) | Q4_1 | 2.56GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [Fallen-Gemma3-4B-v1-Q4_K_M.gguf](https://huggingface.co/bartowski/TheDrummer_Fallen-Gemma3-4B-v1-GGUF/blob/main/TheDrummer_Fallen-Gemma3-4B-v1-Q4_K_M.gguf) | Q4_K_M | 2.49GB | false | Good quality, default size for most use cases, *recommended*. | +| [Fallen-Gemma3-4B-v1-Q3_K_XL.gguf](https://huggingface.co/bartowski/TheDrummer_Fallen-Gemma3-4B-v1-GGUF/blob/main/TheDrummer_Fallen-Gemma3-4B-v1-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. | +| [Fallen-Gemma3-4B-v1-Q4_K_S.gguf](https://huggingface.co/bartowski/TheDrummer_Fallen-Gemma3-4B-v1-GGUF/blob/main/TheDrummer_Fallen-Gemma3-4B-v1-Q4_K_S.gguf) | Q4_K_S | 2.38GB | false | Slightly lower quality with more space savings, *recommended*. | +| [Fallen-Gemma3-4B-v1-Q4_0.gguf](https://huggingface.co/bartowski/TheDrummer_Fallen-Gemma3-4B-v1-GGUF/blob/main/TheDrummer_Fallen-Gemma3-4B-v1-Q4_0.gguf) | Q4_0 | 2.37GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [Fallen-Gemma3-4B-v1-IQ4_NL.gguf](https://huggingface.co/bartowski/TheDrummer_Fallen-Gemma3-4B-v1-GGUF/blob/main/TheDrummer_Fallen-Gemma3-4B-v1-IQ4_NL.gguf) | IQ4_NL | 2.36GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [Fallen-Gemma3-4B-v1-IQ4_XS.gguf](https://huggingface.co/bartowski/TheDrummer_Fallen-Gemma3-4B-v1-GGUF/blob/main/TheDrummer_Fallen-Gemma3-4B-v1-IQ4_XS.gguf) | IQ4_XS | 2.26GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [Fallen-Gemma3-4B-v1-Q3_K_L.gguf](https://huggingface.co/bartowski/TheDrummer_Fallen-Gemma3-4B-v1-GGUF/blob/main/TheDrummer_Fallen-Gemma3-4B-v1-Q3_K_L.gguf) | Q3_K_L | 2.24GB | false | Lower quality but usable, good for low RAM availability. | +| [Fallen-Gemma3-4B-v1-Q3_K_M.gguf](https://huggingface.co/bartowski/TheDrummer_Fallen-Gemma3-4B-v1-GGUF/blob/main/TheDrummer_Fallen-Gemma3-4B-v1-Q3_K_M.gguf) | Q3_K_M | 2.10GB | false | Low quality. | +| [Fallen-Gemma3-4B-v1-IQ3_M.gguf](https://huggingface.co/bartowski/TheDrummer_Fallen-Gemma3-4B-v1-GGUF/blob/main/TheDrummer_Fallen-Gemma3-4B-v1-IQ3_M.gguf) | IQ3_M | 1.99GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [Fallen-Gemma3-4B-v1-Q3_K_S.gguf](https://huggingface.co/bartowski/TheDrummer_Fallen-Gemma3-4B-v1-GGUF/blob/main/TheDrummer_Fallen-Gemma3-4B-v1-Q3_K_S.gguf) | Q3_K_S | 1.94GB | false | Low quality, not recommended. | +| [Fallen-Gemma3-4B-v1-Q2_K_L.gguf](https://huggingface.co/bartowski/TheDrummer_Fallen-Gemma3-4B-v1-GGUF/blob/main/TheDrummer_Fallen-Gemma3-4B-v1-Q2_K_L.gguf) | Q2_K_L | 1.89GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [Fallen-Gemma3-4B-v1-IQ3_XS.gguf](https://huggingface.co/bartowski/TheDrummer_Fallen-Gemma3-4B-v1-GGUF/blob/main/TheDrummer_Fallen-Gemma3-4B-v1-IQ3_XS.gguf) | IQ3_XS | 1.86GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [Fallen-Gemma3-4B-v1-Q2_K.gguf](https://huggingface.co/bartowski/TheDrummer_Fallen-Gemma3-4B-v1-GGUF/blob/main/TheDrummer_Fallen-Gemma3-4B-v1-Q2_K.gguf) | Q2_K | 1.73GB | false | Very low quality but surprisingly usable. | +| [Fallen-Gemma3-4B-v1-IQ3_XXS.gguf](https://huggingface.co/bartowski/TheDrummer_Fallen-Gemma3-4B-v1-GGUF/blob/main/TheDrummer_Fallen-Gemma3-4B-v1-IQ3_XXS.gguf) | IQ3_XXS | 1.69GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [Fallen-Gemma3-4B-v1-IQ2_M.gguf](https://huggingface.co/bartowski/TheDrummer_Fallen-Gemma3-4B-v1-GGUF/blob/main/TheDrummer_Fallen-Gemma3-4B-v1-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/TheDrummer_Fallen-Gemma3-4B-v1-GGUF --include "TheDrummer_Fallen-Gemma3-4B-v1-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/TheDrummer_Fallen-Gemma3-4B-v1-GGUF --include "TheDrummer_Fallen-Gemma3-4B-v1-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (TheDrummer_Fallen-Gemma3-4B-v1-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 diff --git a/TheDrummer_Fallen-Gemma3-4B-v1-IQ2_M.gguf b/TheDrummer_Fallen-Gemma3-4B-v1-IQ2_M.gguf new file mode 100644 index 0000000..2f7f6d3 --- /dev/null +++ b/TheDrummer_Fallen-Gemma3-4B-v1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:035237e052982b8b8d013800e78c0180112769aa9b0db940be22178fc53e591e +size 1537982304 diff --git a/TheDrummer_Fallen-Gemma3-4B-v1-IQ3_M.gguf b/TheDrummer_Fallen-Gemma3-4B-v1-IQ3_M.gguf new file mode 100644 index 0000000..2344e7a --- /dev/null +++ b/TheDrummer_Fallen-Gemma3-4B-v1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da314823b150da2076d5dfe64bc476ce0e8f22e8f7a6658be933eacc66f99ddb +size 1986802784 diff --git a/TheDrummer_Fallen-Gemma3-4B-v1-IQ3_XS.gguf b/TheDrummer_Fallen-Gemma3-4B-v1-IQ3_XS.gguf new file mode 100644 index 0000000..0676224 --- /dev/null +++ b/TheDrummer_Fallen-Gemma3-4B-v1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:892ba0796ca782dd01e9e47b7bfdf41629c06c0230c87ef2260bb383a91a2b75 +size 1863390304 diff --git a/TheDrummer_Fallen-Gemma3-4B-v1-IQ3_XXS.gguf b/TheDrummer_Fallen-Gemma3-4B-v1-IQ3_XXS.gguf new file mode 100644 index 0000000..fb67298 --- /dev/null +++ b/TheDrummer_Fallen-Gemma3-4B-v1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0590724b27aea584651e5bea3a11895f6ba98762994417454e6abbb0ddc4e733 +size 1689452384 diff --git a/TheDrummer_Fallen-Gemma3-4B-v1-IQ4_NL.gguf b/TheDrummer_Fallen-Gemma3-4B-v1-IQ4_NL.gguf new file mode 100644 index 0000000..ba98ba6 --- /dev/null +++ b/TheDrummer_Fallen-Gemma3-4B-v1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65f6d6edb08d7a2c095138c9029dc76796d765bf451de759cdc624781e437da8 +size 2363511904 diff --git a/TheDrummer_Fallen-Gemma3-4B-v1-IQ4_XS.gguf b/TheDrummer_Fallen-Gemma3-4B-v1-IQ4_XS.gguf new file mode 100644 index 0000000..d05e51f --- /dev/null +++ b/TheDrummer_Fallen-Gemma3-4B-v1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:738d9854bd433e4a7911b2bbfb2467d53eacd49968248ec5308ccdbbe53120f7 +size 2263241824 diff --git a/TheDrummer_Fallen-Gemma3-4B-v1-Q2_K.gguf b/TheDrummer_Fallen-Gemma3-4B-v1-Q2_K.gguf new file mode 100644 index 0000000..5d8ecc4 --- /dev/null +++ b/TheDrummer_Fallen-Gemma3-4B-v1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f961da0e3585def78499ac03cff10285026dc4bd0e5b7be2b1c2546377b387fe +size 1729164384 diff --git a/TheDrummer_Fallen-Gemma3-4B-v1-Q2_K_L.gguf b/TheDrummer_Fallen-Gemma3-4B-v1-Q2_K_L.gguf new file mode 100644 index 0000000..8cc5513 --- /dev/null +++ b/TheDrummer_Fallen-Gemma3-4B-v1-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abb739ad00568318077662a85a353f9810d3feeaccfa2a6c1be858fced25401f +size 1891733344 diff --git a/TheDrummer_Fallen-Gemma3-4B-v1-Q3_K_L.gguf b/TheDrummer_Fallen-Gemma3-4B-v1-Q3_K_L.gguf new file mode 100644 index 0000000..39372bb --- /dev/null +++ b/TheDrummer_Fallen-Gemma3-4B-v1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9535af4e019e8509a097999b7259c3f7bc39cf907b61f163959a967cece48058 +size 2236085344 diff --git a/TheDrummer_Fallen-Gemma3-4B-v1-Q3_K_M.gguf b/TheDrummer_Fallen-Gemma3-4B-v1-Q3_K_M.gguf new file mode 100644 index 0000000..e83e5a6 --- /dev/null +++ b/TheDrummer_Fallen-Gemma3-4B-v1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbd1f9e99a3476e2d7bb0a567323676e51d9a34d8ccccd8403cbeff7d6e4e608 +size 2098459744 diff --git a/TheDrummer_Fallen-Gemma3-4B-v1-Q3_K_S.gguf b/TheDrummer_Fallen-Gemma3-4B-v1-Q3_K_S.gguf new file mode 100644 index 0000000..8823fcd --- /dev/null +++ b/TheDrummer_Fallen-Gemma3-4B-v1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd95564d8c5c2123e3a813565ee51da5432ca6adb55a4199d9d6d849b4d519c0 +size 1937364064 diff --git a/TheDrummer_Fallen-Gemma3-4B-v1-Q3_K_XL.gguf b/TheDrummer_Fallen-Gemma3-4B-v1-Q3_K_XL.gguf new file mode 100644 index 0000000..ffc567c --- /dev/null +++ b/TheDrummer_Fallen-Gemma3-4B-v1-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:855fd39554a12e61193cd71d09da56f995a711e34ad4abb2f623b43047aa7460 +size 2398654304 diff --git a/TheDrummer_Fallen-Gemma3-4B-v1-Q4_0.gguf b/TheDrummer_Fallen-Gemma3-4B-v1-Q4_0.gguf new file mode 100644 index 0000000..9ad8211 --- /dev/null +++ b/TheDrummer_Fallen-Gemma3-4B-v1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d663406a9beb7093e0a6128c13d504a21b7f50d218a26b37b66941b5ba583c37 +size 2370065504 diff --git a/TheDrummer_Fallen-Gemma3-4B-v1-Q4_1.gguf b/TheDrummer_Fallen-Gemma3-4B-v1-Q4_1.gguf new file mode 100644 index 0000000..edffa5a --- /dev/null +++ b/TheDrummer_Fallen-Gemma3-4B-v1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7abd61f41470689c59662d53168fb6e9a7c3dbfe3f835d8c545c96d5ba4e8ca6 +size 2564052064 diff --git a/TheDrummer_Fallen-Gemma3-4B-v1-Q4_K_L.gguf b/TheDrummer_Fallen-Gemma3-4B-v1-Q4_K_L.gguf new file mode 100644 index 0000000..b439354 --- /dev/null +++ b/TheDrummer_Fallen-Gemma3-4B-v1-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6f60604d85403dac88388267e55207dd36d053b2fcdb84e43affd4b91ed7507 +size 2652462944 diff --git a/TheDrummer_Fallen-Gemma3-4B-v1-Q4_K_M.gguf b/TheDrummer_Fallen-Gemma3-4B-v1-Q4_K_M.gguf new file mode 100644 index 0000000..f8d87a8 --- /dev/null +++ b/TheDrummer_Fallen-Gemma3-4B-v1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85490a97bda2d40437c8dade4a68bb58e760c1263a2fbc59191daef57ee2d6c3 +size 2489893984 diff --git a/TheDrummer_Fallen-Gemma3-4B-v1-Q4_K_S.gguf b/TheDrummer_Fallen-Gemma3-4B-v1-Q4_K_S.gguf new file mode 100644 index 0000000..4c68ae2 --- /dev/null +++ b/TheDrummer_Fallen-Gemma3-4B-v1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e177fb72f0e34d0dd302c59286a38020370f2a046eee01fefb6bbcf6c3a7aec +size 2377929824 diff --git a/TheDrummer_Fallen-Gemma3-4B-v1-Q5_K_L.gguf b/TheDrummer_Fallen-Gemma3-4B-v1-Q5_K_L.gguf new file mode 100644 index 0000000..f485b66 --- /dev/null +++ b/TheDrummer_Fallen-Gemma3-4B-v1-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:672a665eec10f618d6c43080eb9de2c16ec4fc9c722a5fa908e3bd60f418c6ff +size 2992267104 diff --git a/TheDrummer_Fallen-Gemma3-4B-v1-Q5_K_M.gguf b/TheDrummer_Fallen-Gemma3-4B-v1-Q5_K_M.gguf new file mode 100644 index 0000000..e6a91c7 --- /dev/null +++ b/TheDrummer_Fallen-Gemma3-4B-v1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28f4237c2a7e4d04820b2b25b6b9233c76ce18ba828057bbc0ff23b40e4f3f52 +size 2829698144 diff --git a/TheDrummer_Fallen-Gemma3-4B-v1-Q5_K_S.gguf b/TheDrummer_Fallen-Gemma3-4B-v1-Q5_K_S.gguf new file mode 100644 index 0000000..bc4c4a9 --- /dev/null +++ b/TheDrummer_Fallen-Gemma3-4B-v1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c551821cf987b4a2506c54933dc21ed6098754f190aadebf452cc4f1bccf5482 +size 2764592224 diff --git a/TheDrummer_Fallen-Gemma3-4B-v1-Q6_K.gguf b/TheDrummer_Fallen-Gemma3-4B-v1-Q6_K.gguf new file mode 100644 index 0000000..ab59eba --- /dev/null +++ b/TheDrummer_Fallen-Gemma3-4B-v1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7a08c7856d233ad1a330e4c52044f3bbd0a93dc955092f7652f494442dabdeb +size 3190740064 diff --git a/TheDrummer_Fallen-Gemma3-4B-v1-Q6_K_L.gguf b/TheDrummer_Fallen-Gemma3-4B-v1-Q6_K_L.gguf new file mode 100644 index 0000000..e3a0679 --- /dev/null +++ b/TheDrummer_Fallen-Gemma3-4B-v1-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8f1f8449a8ef2fdd2c9ff1c884093b83de456098d5cc4a3b169e66e3c04dcb5 +size 3353309024 diff --git a/TheDrummer_Fallen-Gemma3-4B-v1-Q8_0.gguf b/TheDrummer_Fallen-Gemma3-4B-v1-Q8_0.gguf new file mode 100644 index 0000000..fb14a56 --- /dev/null +++ b/TheDrummer_Fallen-Gemma3-4B-v1-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e49b169d531b9cdba19a1d56535ad4fda51d2d6047dff6816ef35bad0a34ee88 +size 4130402144 diff --git a/TheDrummer_Fallen-Gemma3-4B-v1-bf16.gguf b/TheDrummer_Fallen-Gemma3-4B-v1-bf16.gguf new file mode 100644 index 0000000..2c93fcd --- /dev/null +++ b/TheDrummer_Fallen-Gemma3-4B-v1-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dadab320b5e62189ea79509ee5a31d33cef5b86c1da6bbab4db4a159086a5c81 +size 7767803456 diff --git a/TheDrummer_Fallen-Gemma3-4B-v1.imatrix b/TheDrummer_Fallen-Gemma3-4B-v1.imatrix new file mode 100644 index 0000000..ef3b844 Binary files /dev/null and b/TheDrummer_Fallen-Gemma3-4B-v1.imatrix differ 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