commit 5bdc2a071590042a30963b122cb9b37f6b7ad851 Author: ModelHub XC Date: Sat Jun 20 23:51:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/allura-org_remnant-qwen3-8b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..bcf24e9 --- /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 + +allura-org_remnant-qwen3-8b.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..734a377 --- /dev/null +++ b/README.md @@ -0,0 +1,176 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +base_model: allura-org/remnant-qwen3-8b +license: apache-2.0 +tags: +- roleplay +- conversational +- axolotl +- qwen +base_model_relation: quantized +--- + +## Llamacpp imatrix Quantizations of remnant-qwen3-8b by allura-org + +Using llama.cpp release b5270 for quantization. + +Original model: https://huggingface.co/allura-org/remnant-qwen3-8b + +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 | +| -------- | ---------- | --------- | ----- | ----------- | +| [remnant-qwen3-8b-bf16.gguf](https://huggingface.co/bartowski/allura-org_remnant-qwen3-8b-GGUF/blob/main/allura-org_remnant-qwen3-8b-bf16.gguf) | bf16 | 16.39GB | false | Full BF16 weights. | +| [remnant-qwen3-8b-Q8_0.gguf](https://huggingface.co/bartowski/allura-org_remnant-qwen3-8b-GGUF/blob/main/allura-org_remnant-qwen3-8b-Q8_0.gguf) | Q8_0 | 8.71GB | false | Extremely high quality, generally unneeded but max available quant. | +| [remnant-qwen3-8b-Q6_K_L.gguf](https://huggingface.co/bartowski/allura-org_remnant-qwen3-8b-GGUF/blob/main/allura-org_remnant-qwen3-8b-Q6_K_L.gguf) | Q6_K_L | 7.03GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [remnant-qwen3-8b-Q6_K.gguf](https://huggingface.co/bartowski/allura-org_remnant-qwen3-8b-GGUF/blob/main/allura-org_remnant-qwen3-8b-Q6_K.gguf) | Q6_K | 6.73GB | false | Very high quality, near perfect, *recommended*. | +| [remnant-qwen3-8b-Q5_K_L.gguf](https://huggingface.co/bartowski/allura-org_remnant-qwen3-8b-GGUF/blob/main/allura-org_remnant-qwen3-8b-Q5_K_L.gguf) | Q5_K_L | 6.24GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [remnant-qwen3-8b-Q5_K_M.gguf](https://huggingface.co/bartowski/allura-org_remnant-qwen3-8b-GGUF/blob/main/allura-org_remnant-qwen3-8b-Q5_K_M.gguf) | Q5_K_M | 5.85GB | false | High quality, *recommended*. | +| [remnant-qwen3-8b-Q5_K_S.gguf](https://huggingface.co/bartowski/allura-org_remnant-qwen3-8b-GGUF/blob/main/allura-org_remnant-qwen3-8b-Q5_K_S.gguf) | Q5_K_S | 5.72GB | false | High quality, *recommended*. | +| [remnant-qwen3-8b-Q4_K_L.gguf](https://huggingface.co/bartowski/allura-org_remnant-qwen3-8b-GGUF/blob/main/allura-org_remnant-qwen3-8b-Q4_K_L.gguf) | Q4_K_L | 5.49GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [remnant-qwen3-8b-Q4_1.gguf](https://huggingface.co/bartowski/allura-org_remnant-qwen3-8b-GGUF/blob/main/allura-org_remnant-qwen3-8b-Q4_1.gguf) | Q4_1 | 5.25GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [remnant-qwen3-8b-Q4_K_M.gguf](https://huggingface.co/bartowski/allura-org_remnant-qwen3-8b-GGUF/blob/main/allura-org_remnant-qwen3-8b-Q4_K_M.gguf) | Q4_K_M | 5.03GB | false | Good quality, default size for most use cases, *recommended*. | +| [remnant-qwen3-8b-Q3_K_XL.gguf](https://huggingface.co/bartowski/allura-org_remnant-qwen3-8b-GGUF/blob/main/allura-org_remnant-qwen3-8b-Q3_K_XL.gguf) | Q3_K_XL | 4.98GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [remnant-qwen3-8b-Q4_K_S.gguf](https://huggingface.co/bartowski/allura-org_remnant-qwen3-8b-GGUF/blob/main/allura-org_remnant-qwen3-8b-Q4_K_S.gguf) | Q4_K_S | 4.80GB | false | Slightly lower quality with more space savings, *recommended*. | +| [remnant-qwen3-8b-Q4_0.gguf](https://huggingface.co/bartowski/allura-org_remnant-qwen3-8b-GGUF/blob/main/allura-org_remnant-qwen3-8b-Q4_0.gguf) | Q4_0 | 4.79GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [remnant-qwen3-8b-IQ4_NL.gguf](https://huggingface.co/bartowski/allura-org_remnant-qwen3-8b-GGUF/blob/main/allura-org_remnant-qwen3-8b-IQ4_NL.gguf) | IQ4_NL | 4.79GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [remnant-qwen3-8b-IQ4_XS.gguf](https://huggingface.co/bartowski/allura-org_remnant-qwen3-8b-GGUF/blob/main/allura-org_remnant-qwen3-8b-IQ4_XS.gguf) | IQ4_XS | 4.56GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [remnant-qwen3-8b-Q3_K_L.gguf](https://huggingface.co/bartowski/allura-org_remnant-qwen3-8b-GGUF/blob/main/allura-org_remnant-qwen3-8b-Q3_K_L.gguf) | Q3_K_L | 4.43GB | false | Lower quality but usable, good for low RAM availability. | +| [remnant-qwen3-8b-Q3_K_M.gguf](https://huggingface.co/bartowski/allura-org_remnant-qwen3-8b-GGUF/blob/main/allura-org_remnant-qwen3-8b-Q3_K_M.gguf) | Q3_K_M | 4.12GB | false | Low quality. | +| [remnant-qwen3-8b-IQ3_M.gguf](https://huggingface.co/bartowski/allura-org_remnant-qwen3-8b-GGUF/blob/main/allura-org_remnant-qwen3-8b-IQ3_M.gguf) | IQ3_M | 3.90GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [remnant-qwen3-8b-Q2_K_L.gguf](https://huggingface.co/bartowski/allura-org_remnant-qwen3-8b-GGUF/blob/main/allura-org_remnant-qwen3-8b-Q2_K_L.gguf) | Q2_K_L | 3.89GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [remnant-qwen3-8b-Q3_K_S.gguf](https://huggingface.co/bartowski/allura-org_remnant-qwen3-8b-GGUF/blob/main/allura-org_remnant-qwen3-8b-Q3_K_S.gguf) | Q3_K_S | 3.77GB | false | Low quality, not recommended. | +| [remnant-qwen3-8b-IQ3_XS.gguf](https://huggingface.co/bartowski/allura-org_remnant-qwen3-8b-GGUF/blob/main/allura-org_remnant-qwen3-8b-IQ3_XS.gguf) | IQ3_XS | 3.63GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [remnant-qwen3-8b-IQ3_XXS.gguf](https://huggingface.co/bartowski/allura-org_remnant-qwen3-8b-GGUF/blob/main/allura-org_remnant-qwen3-8b-IQ3_XXS.gguf) | IQ3_XXS | 3.37GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [remnant-qwen3-8b-Q2_K.gguf](https://huggingface.co/bartowski/allura-org_remnant-qwen3-8b-GGUF/blob/main/allura-org_remnant-qwen3-8b-Q2_K.gguf) | Q2_K | 3.28GB | false | Very low quality but surprisingly usable. | +| [remnant-qwen3-8b-IQ2_M.gguf](https://huggingface.co/bartowski/allura-org_remnant-qwen3-8b-GGUF/blob/main/allura-org_remnant-qwen3-8b-IQ2_M.gguf) | IQ2_M | 3.05GB | 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/allura-org_remnant-qwen3-8b-GGUF --include "allura-org_remnant-qwen3-8b-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/allura-org_remnant-qwen3-8b-GGUF --include "allura-org_remnant-qwen3-8b-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (allura-org_remnant-qwen3-8b-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/allura-org_remnant-qwen3-8b-IQ2_M.gguf b/allura-org_remnant-qwen3-8b-IQ2_M.gguf new file mode 100644 index 0000000..374749a --- /dev/null +++ b/allura-org_remnant-qwen3-8b-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aac0a589b66d8fdf57ab339f943020f673edd196d11e978b191f0653706b9e2e +size 3051910816 diff --git a/allura-org_remnant-qwen3-8b-IQ3_M.gguf b/allura-org_remnant-qwen3-8b-IQ3_M.gguf new file mode 100644 index 0000000..61f636b --- /dev/null +++ b/allura-org_remnant-qwen3-8b-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7ad8d8f593f1408493fbb1b27ebc491a1324e97ae2e4041774d44bb0e1aa1bc +size 3896616608 diff --git a/allura-org_remnant-qwen3-8b-IQ3_XS.gguf b/allura-org_remnant-qwen3-8b-IQ3_XS.gguf new file mode 100644 index 0000000..5a56b31 --- /dev/null +++ b/allura-org_remnant-qwen3-8b-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6077db9e903257778822de88e58fea1d88c09830312448c053e4636191a1083 +size 3626870432 diff --git a/allura-org_remnant-qwen3-8b-IQ3_XXS.gguf b/allura-org_remnant-qwen3-8b-IQ3_XXS.gguf new file mode 100644 index 0000000..a39b726 --- /dev/null +++ b/allura-org_remnant-qwen3-8b-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c43df02726b32c34043e65248452b238eb0a881da8705dac7a0e1abf8e2d4c15 +size 3369629344 diff --git a/allura-org_remnant-qwen3-8b-IQ4_NL.gguf b/allura-org_remnant-qwen3-8b-IQ4_NL.gguf new file mode 100644 index 0000000..4107a6b --- /dev/null +++ b/allura-org_remnant-qwen3-8b-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b985bab4ec61df744e10f48a3eeed66b024e178f231e359300b7842a54deabeb +size 4793620128 diff --git a/allura-org_remnant-qwen3-8b-IQ4_XS.gguf b/allura-org_remnant-qwen3-8b-IQ4_XS.gguf new file mode 100644 index 0000000..0e51c78 --- /dev/null +++ b/allura-org_remnant-qwen3-8b-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31e955acfa2bfddbe2322bd521e620b755c4864e6ac8566548faae33381a31bc +size 4561835680 diff --git a/allura-org_remnant-qwen3-8b-Q2_K.gguf b/allura-org_remnant-qwen3-8b-Q2_K.gguf new file mode 100644 index 0000000..e713b6b --- /dev/null +++ b/allura-org_remnant-qwen3-8b-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97bf503c94ba172d95bf384c8e991aceae3c555a86e5168acf54bed22083e438 +size 3281729184 diff --git a/allura-org_remnant-qwen3-8b-Q2_K_L.gguf b/allura-org_remnant-qwen3-8b-Q2_K_L.gguf new file mode 100644 index 0000000..14fbef5 --- /dev/null +++ b/allura-org_remnant-qwen3-8b-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18cb2c733a4fab7df2e774c16f68589a71609f6d8c8900b2e77bf6f7e23e7461 +size 3889473184 diff --git a/allura-org_remnant-qwen3-8b-Q3_K_L.gguf b/allura-org_remnant-qwen3-8b-Q3_K_L.gguf new file mode 100644 index 0000000..9aaff0e --- /dev/null +++ b/allura-org_remnant-qwen3-8b-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:952d610d441207a505c6e7f46326eba84b0a52dea32f7a126729025a868e2ddb +size 4431390368 diff --git a/allura-org_remnant-qwen3-8b-Q3_K_M.gguf b/allura-org_remnant-qwen3-8b-Q3_K_M.gguf new file mode 100644 index 0000000..ef80be6 --- /dev/null +++ b/allura-org_remnant-qwen3-8b-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68cca37efed585d9dc0b15e7262816f0a2125f6dd2f72944c0da8e6ab155e5cc +size 4124157600 diff --git a/allura-org_remnant-qwen3-8b-Q3_K_S.gguf b/allura-org_remnant-qwen3-8b-Q3_K_S.gguf new file mode 100644 index 0000000..ebf72fe --- /dev/null +++ b/allura-org_remnant-qwen3-8b-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fe95fb5b473dbb70aaa58dbc0022ebf2e2f8d52c8ce5f03acfcd2a290d7157c +size 3769607840 diff --git a/allura-org_remnant-qwen3-8b-Q3_K_XL.gguf b/allura-org_remnant-qwen3-8b-Q3_K_XL.gguf new file mode 100644 index 0000000..04e7af2 --- /dev/null +++ b/allura-org_remnant-qwen3-8b-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1c50c94976a9b105fede5351955826c371d7fa6424501d84fd620e78bfaa3a0 +size 4975928992 diff --git a/allura-org_remnant-qwen3-8b-Q4_0.gguf b/allura-org_remnant-qwen3-8b-Q4_0.gguf new file mode 100644 index 0000000..4035fdf --- /dev/null +++ b/allura-org_remnant-qwen3-8b-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4da546c72d92b1f768afdc57c715c7410813574fef17d924fca9251f8932b04 +size 4787328672 diff --git a/allura-org_remnant-qwen3-8b-Q4_1.gguf b/allura-org_remnant-qwen3-8b-Q4_1.gguf new file mode 100644 index 0000000..ebfe9bf --- /dev/null +++ b/allura-org_remnant-qwen3-8b-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c87b0972f378df7cc7135ee6cea7bcd84561faf84b9e36fab08fd7429221b4f +size 5247751840 diff --git a/allura-org_remnant-qwen3-8b-Q4_K_L.gguf b/allura-org_remnant-qwen3-8b-Q4_K_L.gguf new file mode 100644 index 0000000..5dff03b --- /dev/null +++ b/allura-org_remnant-qwen3-8b-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6d13d38f7ff5486dcdde461db547ff47b131a6941b722097763e2c9d0581965 +size 5489665696 diff --git a/allura-org_remnant-qwen3-8b-Q4_K_M.gguf b/allura-org_remnant-qwen3-8b-Q4_K_M.gguf new file mode 100644 index 0000000..01779aa --- /dev/null +++ b/allura-org_remnant-qwen3-8b-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94e179bb1f1fe0069804a7713bd6b1343626ef11d17a67c6990be7b813d26aeb +size 5027780256 diff --git a/allura-org_remnant-qwen3-8b-Q4_K_S.gguf b/allura-org_remnant-qwen3-8b-Q4_K_S.gguf new file mode 100644 index 0000000..8d69e08 --- /dev/null +++ b/allura-org_remnant-qwen3-8b-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fae2fad4225372c2e31269e281daa330e958e4f3d367abd08f18189d149673b +size 4802008736 diff --git a/allura-org_remnant-qwen3-8b-Q5_K_L.gguf b/allura-org_remnant-qwen3-8b-Q5_K_L.gguf new file mode 100644 index 0000000..dafc8f1 --- /dev/null +++ b/allura-org_remnant-qwen3-8b-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b07083c760ee0f83f5f35aee748bd1adb58f3fb839d73bf421187578f93134af +size 6235203232 diff --git a/allura-org_remnant-qwen3-8b-Q5_K_M.gguf b/allura-org_remnant-qwen3-8b-Q5_K_M.gguf new file mode 100644 index 0000000..9355433 --- /dev/null +++ b/allura-org_remnant-qwen3-8b-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44378c30d5fb9cb15c4e1cdb9d6b48dcecde35f7a0c80d489f34ad273015be6d +size 5851109024 diff --git a/allura-org_remnant-qwen3-8b-Q5_K_S.gguf b/allura-org_remnant-qwen3-8b-Q5_K_S.gguf new file mode 100644 index 0000000..f9bee63 --- /dev/null +++ b/allura-org_remnant-qwen3-8b-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83e845a3d81ba73f8863537e1cc26da3ca3d6ee3ab8fa8aacb00bbcf0a311f40 +size 5720757920 diff --git a/allura-org_remnant-qwen3-8b-Q6_K.gguf b/allura-org_remnant-qwen3-8b-Q6_K.gguf new file mode 100644 index 0000000..156d591 --- /dev/null +++ b/allura-org_remnant-qwen3-8b-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f547e64e76c3130e5fd0a13cf5a80fb415ec8df18a0fb549e473cf8ac147a23 +size 6725895840 diff --git a/allura-org_remnant-qwen3-8b-Q6_K_L.gguf b/allura-org_remnant-qwen3-8b-Q6_K_L.gguf new file mode 100644 index 0000000..9cea108 --- /dev/null +++ b/allura-org_remnant-qwen3-8b-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0297a45a3ad8ace58671169ff2db13187161d565a7099207318936e8a6dfe07b +size 7027336864 diff --git a/allura-org_remnant-qwen3-8b-Q8_0.gguf b/allura-org_remnant-qwen3-8b-Q8_0.gguf new file mode 100644 index 0000000..5952f8b --- /dev/null +++ b/allura-org_remnant-qwen3-8b-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38a9cfe983cd535f2c1bdd20f963627a2bf8e3ef08b28740f75d83ab8fda12c7 +size 8709514912 diff --git a/allura-org_remnant-qwen3-8b-bf16.gguf b/allura-org_remnant-qwen3-8b-bf16.gguf new file mode 100644 index 0000000..176a9d9 --- /dev/null +++ b/allura-org_remnant-qwen3-8b-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86eb0b6d3b933b3e1ea3f9bfeca981031d2465d2458e7375572362cc9e5711b5 +size 16388040064 diff --git a/allura-org_remnant-qwen3-8b.imatrix b/allura-org_remnant-qwen3-8b.imatrix new file mode 100644 index 0000000..df3e93c --- /dev/null +++ b/allura-org_remnant-qwen3-8b.imatrix @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:502c8f5364d0fe013b35dc0ffe66f636be383d6a42de3514fae7a869ed33f5fc +size 5316782 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