commit f38c73d51a8774ba6deeb9cff56be87115229ac6 Author: ModelHub XC Date: Tue May 26 08:34:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-8B-YOYO-V2-Hybrid-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a400482 --- /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 +Qwen3-8B-YOYO-V2-Hybrid.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-YOYO-V2-Hybrid.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-YOYO-V2-Hybrid.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-YOYO-V2-Hybrid.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-YOYO-V2-Hybrid.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-YOYO-V2-Hybrid.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-YOYO-V2-Hybrid.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-YOYO-V2-Hybrid.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-YOYO-V2-Hybrid.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-YOYO-V2-Hybrid.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-YOYO-V2-Hybrid.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-YOYO-V2-Hybrid.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-8B-YOYO-V2-Hybrid.IQ4_XS.gguf b/Qwen3-8B-YOYO-V2-Hybrid.IQ4_XS.gguf new file mode 100644 index 0000000..cf54852 --- /dev/null +++ b/Qwen3-8B-YOYO-V2-Hybrid.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43f430967bf57d68ebe84613885503596ad5674741cc47943ca3c2a4842e2030 +size 4591814304 diff --git a/Qwen3-8B-YOYO-V2-Hybrid.Q2_K.gguf b/Qwen3-8B-YOYO-V2-Hybrid.Q2_K.gguf new file mode 100644 index 0000000..fbf6dc9 --- /dev/null +++ b/Qwen3-8B-YOYO-V2-Hybrid.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:044afb17f71301f0a081385971b89065eda2e8ad52a10ec137a53c3dfb5fd977 +size 3280472672 diff --git a/Qwen3-8B-YOYO-V2-Hybrid.Q3_K_L.gguf b/Qwen3-8B-YOYO-V2-Hybrid.Q3_K_L.gguf new file mode 100644 index 0000000..863ec52 --- /dev/null +++ b/Qwen3-8B-YOYO-V2-Hybrid.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbbee6220ce43668bc5aecf9eeb42e042e5de6bb86fc67408b20f00b1301f75e +size 4430022784 diff --git a/Qwen3-8B-YOYO-V2-Hybrid.Q3_K_M.gguf b/Qwen3-8B-YOYO-V2-Hybrid.Q3_K_M.gguf new file mode 100644 index 0000000..2c9c904 --- /dev/null +++ b/Qwen3-8B-YOYO-V2-Hybrid.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f8530099af583175770e7274b265cbf5069efec1490ecbfae008a914d270460 +size 4122790016 diff --git a/Qwen3-8B-YOYO-V2-Hybrid.Q3_K_S.gguf b/Qwen3-8B-YOYO-V2-Hybrid.Q3_K_S.gguf new file mode 100644 index 0000000..60e115a --- /dev/null +++ b/Qwen3-8B-YOYO-V2-Hybrid.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1953a8a1ce43cff627c2bc5f8d928c893a14ae6b4336f8221ff3eff8c8d2ab0b +size 3768240256 diff --git a/Qwen3-8B-YOYO-V2-Hybrid.Q4_K_M.gguf b/Qwen3-8B-YOYO-V2-Hybrid.Q4_K_M.gguf new file mode 100644 index 0000000..5590760 --- /dev/null +++ b/Qwen3-8B-YOYO-V2-Hybrid.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a45e5800856f33b54cf49d3a6f12d2a214ac0e485f684752803125f3896cea4a +size 5026267424 diff --git a/Qwen3-8B-YOYO-V2-Hybrid.Q4_K_S.gguf b/Qwen3-8B-YOYO-V2-Hybrid.Q4_K_S.gguf new file mode 100644 index 0000000..e28065d --- /dev/null +++ b/Qwen3-8B-YOYO-V2-Hybrid.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6f221686e1915cbfd3be2e438d361162201b1a8031bb950dc51144da38eca61 +size 4800495904 diff --git a/Qwen3-8B-YOYO-V2-Hybrid.Q5_K_M.gguf b/Qwen3-8B-YOYO-V2-Hybrid.Q5_K_M.gguf new file mode 100644 index 0000000..f21ce60 --- /dev/null +++ b/Qwen3-8B-YOYO-V2-Hybrid.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14edea29c62b35467653508996247dac60a40262cb9a11f08ceb1c6f1185a007 +size 5849459488 diff --git a/Qwen3-8B-YOYO-V2-Hybrid.Q5_K_S.gguf b/Qwen3-8B-YOYO-V2-Hybrid.Q5_K_S.gguf new file mode 100644 index 0000000..e511cfb --- /dev/null +++ b/Qwen3-8B-YOYO-V2-Hybrid.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b8d15952acfe39902bb8574a9804f8aa8bae55ff0796ac37599d15e30af77b1 +size 5719108384 diff --git a/Qwen3-8B-YOYO-V2-Hybrid.Q6_K.gguf b/Qwen3-8B-YOYO-V2-Hybrid.Q6_K.gguf new file mode 100644 index 0000000..999ea4d --- /dev/null +++ b/Qwen3-8B-YOYO-V2-Hybrid.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95f3e46ef7bf71cdbe5d3b54b5a2f1020a243d83e22b2d77748af3ae55450a86 +size 6724101056 diff --git a/Qwen3-8B-YOYO-V2-Hybrid.Q8_0.gguf b/Qwen3-8B-YOYO-V2-Hybrid.Q8_0.gguf new file mode 100644 index 0000000..142d0a3 --- /dev/null +++ b/Qwen3-8B-YOYO-V2-Hybrid.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13e36fc5f51fd4be283f24bce1c7fac6cec0ecc17ef35a27302219cad808f507 +size 8707190400 diff --git a/Qwen3-8B-YOYO-V2-Hybrid.f16.gguf b/Qwen3-8B-YOYO-V2-Hybrid.f16.gguf new file mode 100644 index 0000000..2f1b3e0 --- /dev/null +++ b/Qwen3-8B-YOYO-V2-Hybrid.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e059d5625315fe5bf7975607814d79ce001ef16cede9e7158fb79b80704e6a7 +size 16383665280 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f09c2db --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: YOYO-AI/Qwen3-8B-YOYO-V2-Hybrid +language: +- en +- zh +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- merge +--- +## About + + + + + + + + + +static quants of https://huggingface.co/YOYO-AI/Qwen3-8B-YOYO-V2-Hybrid + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-8B-YOYO-V2-Hybrid-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-8B-YOYO-V2-Hybrid-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/Qwen3-8B-YOYO-V2-Hybrid-GGUF/resolve/main/Qwen3-8B-YOYO-V2-Hybrid.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-YOYO-V2-Hybrid-GGUF/resolve/main/Qwen3-8B-YOYO-V2-Hybrid.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-YOYO-V2-Hybrid-GGUF/resolve/main/Qwen3-8B-YOYO-V2-Hybrid.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-YOYO-V2-Hybrid-GGUF/resolve/main/Qwen3-8B-YOYO-V2-Hybrid.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-YOYO-V2-Hybrid-GGUF/resolve/main/Qwen3-8B-YOYO-V2-Hybrid.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-YOYO-V2-Hybrid-GGUF/resolve/main/Qwen3-8B-YOYO-V2-Hybrid.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-YOYO-V2-Hybrid-GGUF/resolve/main/Qwen3-8B-YOYO-V2-Hybrid.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-YOYO-V2-Hybrid-GGUF/resolve/main/Qwen3-8B-YOYO-V2-Hybrid.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-YOYO-V2-Hybrid-GGUF/resolve/main/Qwen3-8B-YOYO-V2-Hybrid.Q5_K_M.gguf) | Q5_K_M | 5.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-YOYO-V2-Hybrid-GGUF/resolve/main/Qwen3-8B-YOYO-V2-Hybrid.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-YOYO-V2-Hybrid-GGUF/resolve/main/Qwen3-8B-YOYO-V2-Hybrid.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-YOYO-V2-Hybrid-GGUF/resolve/main/Qwen3-8B-YOYO-V2-Hybrid.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. + +