commit 5835d02c308343e1280308f59798dcbe1059f140 Author: ModelHub XC Date: Sun Jun 21 20:34:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/kalomaze_Qwen3-16B-A3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f0085a7 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 + +kalomaze_Qwen3-16B-A3B.imatrix 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..160750c --- /dev/null +++ b/README.md @@ -0,0 +1,174 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +license: apache-2.0 +base_model_relation: quantized +base_model: kalomaze/Qwen3-16B-A3B +--- + +## Llamacpp imatrix Quantizations of Qwen3-16B-A3B by kalomaze + +Using llama.cpp release b5255 for quantization. + +Original model: https://huggingface.co/kalomaze/Qwen3-16B-A3B + +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 + +``` +<|im_start|>system +{system_prompt}<|im_end|> +<|im_start|>user +{prompt}<|im_end|> +<|im_start|>assistant +``` + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [Qwen3-16B-A3B-bf16.gguf](https://huggingface.co/bartowski/kalomaze_Qwen3-16B-A3B-GGUF/blob/main/kalomaze_Qwen3-16B-A3B-bf16.gguf) | bf16 | 32.08GB | false | Full BF16 weights. | +| [Qwen3-16B-A3B-Q8_0.gguf](https://huggingface.co/bartowski/kalomaze_Qwen3-16B-A3B-GGUF/blob/main/kalomaze_Qwen3-16B-A3B-Q8_0.gguf) | Q8_0 | 17.06GB | false | Extremely high quality, generally unneeded but max available quant. | +| [Qwen3-16B-A3B-Q6_K_L.gguf](https://huggingface.co/bartowski/kalomaze_Qwen3-16B-A3B-GGUF/blob/main/kalomaze_Qwen3-16B-A3B-Q6_K_L.gguf) | Q6_K_L | 13.34GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [Qwen3-16B-A3B-Q6_K.gguf](https://huggingface.co/bartowski/kalomaze_Qwen3-16B-A3B-GGUF/blob/main/kalomaze_Qwen3-16B-A3B-Q6_K.gguf) | Q6_K | 13.19GB | false | Very high quality, near perfect, *recommended*. | +| [Qwen3-16B-A3B-Q5_K_L.gguf](https://huggingface.co/bartowski/kalomaze_Qwen3-16B-A3B-GGUF/blob/main/kalomaze_Qwen3-16B-A3B-Q5_K_L.gguf) | Q5_K_L | 11.62GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [Qwen3-16B-A3B-Q5_K_M.gguf](https://huggingface.co/bartowski/kalomaze_Qwen3-16B-A3B-GGUF/blob/main/kalomaze_Qwen3-16B-A3B-Q5_K_M.gguf) | Q5_K_M | 11.43GB | false | High quality, *recommended*. | +| [Qwen3-16B-A3B-Q5_K_S.gguf](https://huggingface.co/bartowski/kalomaze_Qwen3-16B-A3B-GGUF/blob/main/kalomaze_Qwen3-16B-A3B-Q5_K_S.gguf) | Q5_K_S | 11.11GB | false | High quality, *recommended*. | +| [Qwen3-16B-A3B-Q4_1.gguf](https://huggingface.co/bartowski/kalomaze_Qwen3-16B-A3B-GGUF/blob/main/kalomaze_Qwen3-16B-A3B-Q4_1.gguf) | Q4_1 | 10.13GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [Qwen3-16B-A3B-Q4_K_L.gguf](https://huggingface.co/bartowski/kalomaze_Qwen3-16B-A3B-GGUF/blob/main/kalomaze_Qwen3-16B-A3B-Q4_K_L.gguf) | Q4_K_L | 10.06GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [Qwen3-16B-A3B-Q4_K_M.gguf](https://huggingface.co/bartowski/kalomaze_Qwen3-16B-A3B-GGUF/blob/main/kalomaze_Qwen3-16B-A3B-Q4_K_M.gguf) | Q4_K_M | 9.83GB | false | Good quality, default size for most use cases, *recommended*. | +| [Qwen3-16B-A3B-Q4_K_S.gguf](https://huggingface.co/bartowski/kalomaze_Qwen3-16B-A3B-GGUF/blob/main/kalomaze_Qwen3-16B-A3B-Q4_K_S.gguf) | Q4_K_S | 9.50GB | false | Slightly lower quality with more space savings, *recommended*. | +| [Qwen3-16B-A3B-Q4_0.gguf](https://huggingface.co/bartowski/kalomaze_Qwen3-16B-A3B-GGUF/blob/main/kalomaze_Qwen3-16B-A3B-Q4_0.gguf) | Q4_0 | 9.30GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [Qwen3-16B-A3B-IQ4_NL.gguf](https://huggingface.co/bartowski/kalomaze_Qwen3-16B-A3B-GGUF/blob/main/kalomaze_Qwen3-16B-A3B-IQ4_NL.gguf) | IQ4_NL | 9.21GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [Qwen3-16B-A3B-IQ4_XS.gguf](https://huggingface.co/bartowski/kalomaze_Qwen3-16B-A3B-GGUF/blob/main/kalomaze_Qwen3-16B-A3B-IQ4_XS.gguf) | IQ4_XS | 8.73GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [Qwen3-16B-A3B-Q3_K_XL.gguf](https://huggingface.co/bartowski/kalomaze_Qwen3-16B-A3B-GGUF/blob/main/kalomaze_Qwen3-16B-A3B-Q3_K_XL.gguf) | Q3_K_XL | 7.98GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [Qwen3-16B-A3B-Q3_K_L.gguf](https://huggingface.co/bartowski/kalomaze_Qwen3-16B-A3B-GGUF/blob/main/kalomaze_Qwen3-16B-A3B-Q3_K_L.gguf) | Q3_K_L | 7.71GB | false | Lower quality but usable, good for low RAM availability. | +| [Qwen3-16B-A3B-Q3_K_M.gguf](https://huggingface.co/bartowski/kalomaze_Qwen3-16B-A3B-GGUF/blob/main/kalomaze_Qwen3-16B-A3B-Q3_K_M.gguf) | Q3_K_M | 7.50GB | false | Low quality. | +| [Qwen3-16B-A3B-IQ3_M.gguf](https://huggingface.co/bartowski/kalomaze_Qwen3-16B-A3B-GGUF/blob/main/kalomaze_Qwen3-16B-A3B-IQ3_M.gguf) | IQ3_M | 7.50GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [Qwen3-16B-A3B-Q3_K_S.gguf](https://huggingface.co/bartowski/kalomaze_Qwen3-16B-A3B-GGUF/blob/main/kalomaze_Qwen3-16B-A3B-Q3_K_S.gguf) | Q3_K_S | 7.17GB | false | Low quality, not recommended. | +| [Qwen3-16B-A3B-IQ3_XS.gguf](https://huggingface.co/bartowski/kalomaze_Qwen3-16B-A3B-GGUF/blob/main/kalomaze_Qwen3-16B-A3B-IQ3_XS.gguf) | IQ3_XS | 6.82GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [Qwen3-16B-A3B-IQ3_XXS.gguf](https://huggingface.co/bartowski/kalomaze_Qwen3-16B-A3B-GGUF/blob/main/kalomaze_Qwen3-16B-A3B-IQ3_XXS.gguf) | IQ3_XXS | 6.53GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [Qwen3-16B-A3B-Q2_K_L.gguf](https://huggingface.co/bartowski/kalomaze_Qwen3-16B-A3B-GGUF/blob/main/kalomaze_Qwen3-16B-A3B-Q2_K_L.gguf) | Q2_K_L | 6.19GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [Qwen3-16B-A3B-Q2_K.gguf](https://huggingface.co/bartowski/kalomaze_Qwen3-16B-A3B-GGUF/blob/main/kalomaze_Qwen3-16B-A3B-Q2_K.gguf) | Q2_K | 5.88GB | false | Very low quality but surprisingly usable. | +| [Qwen3-16B-A3B-IQ2_M.gguf](https://huggingface.co/bartowski/kalomaze_Qwen3-16B-A3B-GGUF/blob/main/kalomaze_Qwen3-16B-A3B-IQ2_M.gguf) | IQ2_M | 5.62GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. | +| [Qwen3-16B-A3B-IQ2_S.gguf](https://huggingface.co/bartowski/kalomaze_Qwen3-16B-A3B-GGUF/blob/main/kalomaze_Qwen3-16B-A3B-IQ2_S.gguf) | IQ2_S | 5.01GB | false | Low quality, uses SOTA techniques to be usable. | +| [Qwen3-16B-A3B-IQ2_XS.gguf](https://huggingface.co/bartowski/kalomaze_Qwen3-16B-A3B-GGUF/blob/main/kalomaze_Qwen3-16B-A3B-IQ2_XS.gguf) | IQ2_XS | 4.93GB | false | Low quality, uses SOTA techniques to be usable. | +| [Qwen3-16B-A3B-IQ2_XXS.gguf](https://huggingface.co/bartowski/kalomaze_Qwen3-16B-A3B-GGUF/blob/main/kalomaze_Qwen3-16B-A3B-IQ2_XXS.gguf) | IQ2_XXS | 4.43GB | false | Very low quality, uses SOTA techniques to be usable. | + +## Embed/output weights + +Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to. + +## Downloading using huggingface-cli + +
+ 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/kalomaze_Qwen3-16B-A3B-GGUF --include "kalomaze_Qwen3-16B-A3B-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/kalomaze_Qwen3-16B-A3B-GGUF --include "kalomaze_Qwen3-16B-A3B-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (kalomaze_Qwen3-16B-A3B-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/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/kalomaze_Qwen3-16B-A3B-IQ2_M.gguf b/kalomaze_Qwen3-16B-A3B-IQ2_M.gguf new file mode 100644 index 0000000..6630945 --- /dev/null +++ b/kalomaze_Qwen3-16B-A3B-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd083563153ea6fb0f5f698ed162fd5b0da5a9ce2bdd2e46b7a9901a3f4428a2 +size 5623537696 diff --git a/kalomaze_Qwen3-16B-A3B-IQ2_S.gguf b/kalomaze_Qwen3-16B-A3B-IQ2_S.gguf new file mode 100644 index 0000000..88a429e --- /dev/null +++ b/kalomaze_Qwen3-16B-A3B-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fcd16961a021c1074488b5ff28686d28df5b90758e65346fd8ce91035fed131 +size 5013266464 diff --git a/kalomaze_Qwen3-16B-A3B-IQ2_XS.gguf b/kalomaze_Qwen3-16B-A3B-IQ2_XS.gguf new file mode 100644 index 0000000..fa91fc2 --- /dev/null +++ b/kalomaze_Qwen3-16B-A3B-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:173d437a7ccddfd31acc5e09917658433aa5b061d8647bb1990ad818e0323815 +size 4931332128 diff --git a/kalomaze_Qwen3-16B-A3B-IQ2_XXS.gguf b/kalomaze_Qwen3-16B-A3B-IQ2_XXS.gguf new file mode 100644 index 0000000..5d25adb --- /dev/null +++ b/kalomaze_Qwen3-16B-A3B-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a49300090b729ad5ac1ccbfc55dadfedcae697cfb3b2e1aaf00a29e6e3ffa4a1 +size 4428015648 diff --git a/kalomaze_Qwen3-16B-A3B-IQ3_M.gguf b/kalomaze_Qwen3-16B-A3B-IQ3_M.gguf new file mode 100644 index 0000000..7c628a0 --- /dev/null +++ b/kalomaze_Qwen3-16B-A3B-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f82b82d63327534a037e3149fb5ffcb439c0efa1830e50db5967e9fd562b58c3 +size 7501969440 diff --git a/kalomaze_Qwen3-16B-A3B-IQ3_XS.gguf b/kalomaze_Qwen3-16B-A3B-IQ3_XS.gguf new file mode 100644 index 0000000..52eca93 --- /dev/null +++ b/kalomaze_Qwen3-16B-A3B-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e72377b8358ccf1b09dd1fd51be02d66ac1475af6fba895505d69f0dd83793e +size 6822492192 diff --git a/kalomaze_Qwen3-16B-A3B-IQ3_XXS.gguf b/kalomaze_Qwen3-16B-A3B-IQ3_XXS.gguf new file mode 100644 index 0000000..a733095 --- /dev/null +++ b/kalomaze_Qwen3-16B-A3B-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0360194630c0ffe965d2fb19c42397186d26c1c8a474d372bc3420fc247b4b7 +size 6529507360 diff --git a/kalomaze_Qwen3-16B-A3B-IQ4_NL.gguf b/kalomaze_Qwen3-16B-A3B-IQ4_NL.gguf new file mode 100644 index 0000000..c752878 --- /dev/null +++ b/kalomaze_Qwen3-16B-A3B-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdcebbbc4668b095e38b3b7c49d4b6ea02dd1d776c23cf46e66c056397fcd33c +size 9207386144 diff --git a/kalomaze_Qwen3-16B-A3B-IQ4_XS.gguf b/kalomaze_Qwen3-16B-A3B-IQ4_XS.gguf new file mode 100644 index 0000000..c0f5d31 --- /dev/null +++ b/kalomaze_Qwen3-16B-A3B-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5edc516a37ca30936a558856da71f497489aee8d3053c96541ca512cdb92058f +size 8732094496 diff --git a/kalomaze_Qwen3-16B-A3B-Q2_K.gguf b/kalomaze_Qwen3-16B-A3B-Q2_K.gguf new file mode 100644 index 0000000..dd1036c --- /dev/null +++ b/kalomaze_Qwen3-16B-A3B-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bde6bfbfccd4326f241435db1863c817e808f6d4d74cadce829135dc788c54e +size 5881774112 diff --git a/kalomaze_Qwen3-16B-A3B-Q2_K_L.gguf b/kalomaze_Qwen3-16B-A3B-Q2_K_L.gguf new file mode 100644 index 0000000..9fcd1e6 --- /dev/null +++ b/kalomaze_Qwen3-16B-A3B-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ea81b65dfea73757eb9b4d6bc6553886848433d318e1e3747ab70e4316c9de2 +size 6185646112 diff --git a/kalomaze_Qwen3-16B-A3B-Q3_K_L.gguf b/kalomaze_Qwen3-16B-A3B-Q3_K_L.gguf new file mode 100644 index 0000000..6e819b3 --- /dev/null +++ b/kalomaze_Qwen3-16B-A3B-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45e0660bef48e0da6464946c66d0c23747d358f6856cd388c1a14bb2c3bca4c5 +size 7706441760 diff --git a/kalomaze_Qwen3-16B-A3B-Q3_K_M.gguf b/kalomaze_Qwen3-16B-A3B-Q3_K_M.gguf new file mode 100644 index 0000000..fbe1e39 --- /dev/null +++ b/kalomaze_Qwen3-16B-A3B-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fba7cea59a334911273abc1bcfd7f43f899d351b32db068e450fc3561ee4caa4 +size 7502231584 diff --git a/kalomaze_Qwen3-16B-A3B-Q3_K_S.gguf b/kalomaze_Qwen3-16B-A3B-Q3_K_S.gguf new file mode 100644 index 0000000..edb4ea7 --- /dev/null +++ b/kalomaze_Qwen3-16B-A3B-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f6fdd762dd66773930ededa50979e6d6510e9e93c228913971b0c0b23159f02 +size 7174420512 diff --git a/kalomaze_Qwen3-16B-A3B-Q3_K_XL.gguf b/kalomaze_Qwen3-16B-A3B-Q3_K_XL.gguf new file mode 100644 index 0000000..f5129a1 --- /dev/null +++ b/kalomaze_Qwen3-16B-A3B-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5451a7199b2741eb0a0da04c59becede71aa2575ab5f9053ed8355db0f937866 +size 7978711072 diff --git a/kalomaze_Qwen3-16B-A3B-Q4_0.gguf b/kalomaze_Qwen3-16B-A3B-Q4_0.gguf new file mode 100644 index 0000000..4cc1719 --- /dev/null +++ b/kalomaze_Qwen3-16B-A3B-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a31e6543197ca9a23c597efda1e6d6451e069a2bddda863e32a393af00446ae0 +size 9301757984 diff --git a/kalomaze_Qwen3-16B-A3B-Q4_1.gguf b/kalomaze_Qwen3-16B-A3B-Q4_1.gguf new file mode 100644 index 0000000..9a6a0b8 --- /dev/null +++ b/kalomaze_Qwen3-16B-A3B-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e952532ce0511a21fb5849cfd85cd0d29f24f1c5a92a6f01e5c88d8f52acc7e0 +size 10129657888 diff --git a/kalomaze_Qwen3-16B-A3B-Q4_K_L.gguf b/kalomaze_Qwen3-16B-A3B-Q4_K_L.gguf new file mode 100644 index 0000000..a09dd47 --- /dev/null +++ b/kalomaze_Qwen3-16B-A3B-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcf9b613387e2e78e896b1bfd8a2f5f6052b23361d89b712f264d77b809eb05a +size 10061379616 diff --git a/kalomaze_Qwen3-16B-A3B-Q4_K_M.gguf b/kalomaze_Qwen3-16B-A3B-Q4_K_M.gguf new file mode 100644 index 0000000..61f28be --- /dev/null +++ b/kalomaze_Qwen3-16B-A3B-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34c86e1a956349632a05af37a104203823859363f141e1002abe6017349fbdcb +size 9830436896 diff --git a/kalomaze_Qwen3-16B-A3B-Q4_K_S.gguf b/kalomaze_Qwen3-16B-A3B-Q4_K_S.gguf new file mode 100644 index 0000000..1c09115 --- /dev/null +++ b/kalomaze_Qwen3-16B-A3B-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:609ebf791a52262830acfc4f435c5a88b900f0ab8e715932d24aaff2da662d94 +size 9503608864 diff --git a/kalomaze_Qwen3-16B-A3B-Q5_K_L.gguf b/kalomaze_Qwen3-16B-A3B-Q5_K_L.gguf new file mode 100644 index 0000000..c296ea2 --- /dev/null +++ b/kalomaze_Qwen3-16B-A3B-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb673308798f4226060fbb97dcf284596d8f8d74ba837aa3fd1a138abef2f4fc +size 11624806432 diff --git a/kalomaze_Qwen3-16B-A3B-Q5_K_M.gguf b/kalomaze_Qwen3-16B-A3B-Q5_K_M.gguf new file mode 100644 index 0000000..bb2a7ff --- /dev/null +++ b/kalomaze_Qwen3-16B-A3B-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47eba53909eca4233283dc22352c69d11213215cd648fb053c41b3e9362889f2 +size 11432759328 diff --git a/kalomaze_Qwen3-16B-A3B-Q5_K_S.gguf b/kalomaze_Qwen3-16B-A3B-Q5_K_S.gguf new file mode 100644 index 0000000..09df7b2 --- /dev/null +++ b/kalomaze_Qwen3-16B-A3B-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b50e43409fd638f3602db5a9eca306f9a6d755ae56ee19dff7b15c535f1a7461 +size 11108552736 diff --git a/kalomaze_Qwen3-16B-A3B-Q6_K.gguf b/kalomaze_Qwen3-16B-A3B-Q6_K.gguf new file mode 100644 index 0000000..10d8fa3 --- /dev/null +++ b/kalomaze_Qwen3-16B-A3B-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb0740e90f1804a0d7a14b08046441954653d0d73fe2d48c95a88e6e3ed7d229 +size 13188704288 diff --git a/kalomaze_Qwen3-16B-A3B-Q6_K_L.gguf b/kalomaze_Qwen3-16B-A3B-Q6_K_L.gguf new file mode 100644 index 0000000..06d8091 --- /dev/null +++ b/kalomaze_Qwen3-16B-A3B-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ae92e8adad2879abfdcd96dd2b55cc6d7c46b964a2d9a659d7c2be306ec6bda +size 13339424800 diff --git a/kalomaze_Qwen3-16B-A3B-Q8_0.gguf b/kalomaze_Qwen3-16B-A3B-Q8_0.gguf new file mode 100644 index 0000000..6787bee --- /dev/null +++ b/kalomaze_Qwen3-16B-A3B-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f18222e4072ee678fef675088ae358cdc0131df67e82a88958aeee04f21d23a1 +size 17057282080 diff --git a/kalomaze_Qwen3-16B-A3B-bf16.gguf b/kalomaze_Qwen3-16B-A3B-bf16.gguf new file mode 100644 index 0000000..73448a6 --- /dev/null +++ b/kalomaze_Qwen3-16B-A3B-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9697b4110c47ce9459b4101c42e885e541418f5e5c6d7402ddf12d8312fee3c6 +size 32079607552 diff --git a/kalomaze_Qwen3-16B-A3B.imatrix b/kalomaze_Qwen3-16B-A3B.imatrix new file mode 100644 index 0000000..71bbacf --- /dev/null +++ b/kalomaze_Qwen3-16B-A3B.imatrix @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28ecdf4ec63932325056a2cd410d16ee4f1f32001b519029b64feb89c058b340 +size 62141824