commit 2b02b847624b71a9473d53b934eb639056291ac1 Author: ModelHub XC Date: Thu Jul 16 15:37:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-XPlus-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..93fe7d5 --- /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 +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt 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 +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz 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 +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl 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 +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* 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 +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +Qwen3-XPlus-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-XPlus-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-XPlus-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-XPlus-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-XPlus-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-XPlus-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-XPlus-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-XPlus-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-XPlus-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-XPlus-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-XPlus-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-XPlus-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-XPlus-8B.IQ4_XS.gguf b/Qwen3-XPlus-8B.IQ4_XS.gguf new file mode 100644 index 0000000..ab675be --- /dev/null +++ b/Qwen3-XPlus-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:621c69de84bc97346bb3fdbd8dfbce5c10620307c1aacb07b6dbc14b362d5b3e +size 4593296960 diff --git a/Qwen3-XPlus-8B.Q2_K.gguf b/Qwen3-XPlus-8B.Q2_K.gguf new file mode 100644 index 0000000..34d94b7 --- /dev/null +++ b/Qwen3-XPlus-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b14d1a07e7e1316b6e805fe4145924e3cab7ee0a4a0852d46293f37194b5c4e +size 3281733184 diff --git a/Qwen3-XPlus-8B.Q3_K_L.gguf b/Qwen3-XPlus-8B.Q3_K_L.gguf new file mode 100644 index 0000000..eb9fa09 --- /dev/null +++ b/Qwen3-XPlus-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:512d35cb97a435acbcfe4723f5b0ad21e0e24f53d709ec59c255d45ffcf41748 +size 4431394368 diff --git a/Qwen3-XPlus-8B.Q3_K_M.gguf b/Qwen3-XPlus-8B.Q3_K_M.gguf new file mode 100644 index 0000000..e0ee1b6 --- /dev/null +++ b/Qwen3-XPlus-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94aecdc9f77abb27612a693cbbd125015850805ee99898cf353ad3ac53cffb08 +size 4124161600 diff --git a/Qwen3-XPlus-8B.Q3_K_S.gguf b/Qwen3-XPlus-8B.Q3_K_S.gguf new file mode 100644 index 0000000..c150b21 --- /dev/null +++ b/Qwen3-XPlus-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17b80eb5d03d5a7a92b03b99fc0a1e00a7e43a0d3036e6ebeeef8efdbc5d9d70 +size 3769611840 diff --git a/Qwen3-XPlus-8B.Q4_K_M.gguf b/Qwen3-XPlus-8B.Q4_K_M.gguf new file mode 100644 index 0000000..b9b61e7 --- /dev/null +++ b/Qwen3-XPlus-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfc32a36e5dc960f4febfaf69570687dc54626d7d0aaca81cfa20cd6b43231aa +size 5027784256 diff --git a/Qwen3-XPlus-8B.Q4_K_S.gguf b/Qwen3-XPlus-8B.Q4_K_S.gguf new file mode 100644 index 0000000..0633939 --- /dev/null +++ b/Qwen3-XPlus-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02e149ca762c18bdb4cc8b42195ce671aeae925e694ae7508af1a55869977b7f +size 4802012736 diff --git a/Qwen3-XPlus-8B.Q5_K_M.gguf b/Qwen3-XPlus-8B.Q5_K_M.gguf new file mode 100644 index 0000000..9555667 --- /dev/null +++ b/Qwen3-XPlus-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:053d4e8dfd4096a1e681805cdaf3398b9d5e0b6eafb6ed31e8f681a678a69b22 +size 5851113024 diff --git a/Qwen3-XPlus-8B.Q5_K_S.gguf b/Qwen3-XPlus-8B.Q5_K_S.gguf new file mode 100644 index 0000000..39cf387 --- /dev/null +++ b/Qwen3-XPlus-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f44a77cd8d570fc72bd25a96ac70cf235bfaeb1747ab7b40c70ddc7e67ff899f +size 5720761920 diff --git a/Qwen3-XPlus-8B.Q6_K.gguf b/Qwen3-XPlus-8B.Q6_K.gguf new file mode 100644 index 0000000..141884c --- /dev/null +++ b/Qwen3-XPlus-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:954379fa8c55b58360ab1c80805c568d2611ad131d8fcba3431d128db2c71489 +size 6725899840 diff --git a/Qwen3-XPlus-8B.Q8_0.gguf b/Qwen3-XPlus-8B.Q8_0.gguf new file mode 100644 index 0000000..e561392 --- /dev/null +++ b/Qwen3-XPlus-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9377d4323348e047d5c41183a1f02e480d40c2ef48b5b41c5bafc86ac4592958 +size 8709518912 diff --git a/Qwen3-XPlus-8B.f16.gguf b/Qwen3-XPlus-8B.f16.gguf new file mode 100644 index 0000000..3fba08f --- /dev/null +++ b/Qwen3-XPlus-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6bef387af05ea9e394a6e6cdc2654aae8fe2d6d89ac0ec3893d00436d42f23a +size 16388044352 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b044891 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: LLaMAX/GlotMAX-17-8B +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- llama-factory +- freeze +- generated_from_trainer +--- +## About + + + + + + + + + +static quants of https://huggingface.co/LLaMAX/GlotMAX-17-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-XPlus-8B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-XPlus-8B-i1-GGUF +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/Qwen3-XPlus-8B-GGUF/resolve/main/Qwen3-XPlus-8B.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-XPlus-8B-GGUF/resolve/main/Qwen3-XPlus-8B.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-XPlus-8B-GGUF/resolve/main/Qwen3-XPlus-8B.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-XPlus-8B-GGUF/resolve/main/Qwen3-XPlus-8B.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-XPlus-8B-GGUF/resolve/main/Qwen3-XPlus-8B.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-XPlus-8B-GGUF/resolve/main/Qwen3-XPlus-8B.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-XPlus-8B-GGUF/resolve/main/Qwen3-XPlus-8B.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-XPlus-8B-GGUF/resolve/main/Qwen3-XPlus-8B.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-XPlus-8B-GGUF/resolve/main/Qwen3-XPlus-8B.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-XPlus-8B-GGUF/resolve/main/Qwen3-XPlus-8B.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-XPlus-8B-GGUF/resolve/main/Qwen3-XPlus-8B.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-XPlus-8B-GGUF/resolve/main/Qwen3-XPlus-8B.f16.gguf) | f16 | 16.5 | 16 bpw, overkill | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + +