commit 21ba5a2c29845b47b6f49a78ced786c673d6f2ae Author: ModelHub XC Date: Sat Aug 8 23:44:36 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-ASR-1.7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0ff1104 --- /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 +*.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-ASR-1.7B.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-ASR-1.7B.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-ASR-1.7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-ASR-1.7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-ASR-1.7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-ASR-1.7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-ASR-1.7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-ASR-1.7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-ASR-1.7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-ASR-1.7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-ASR-1.7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-ASR-1.7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-ASR-1.7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-ASR-1.7B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-ASR-1.7B.IQ4_XS.gguf b/Qwen3-ASR-1.7B.IQ4_XS.gguf new file mode 100644 index 0000000..79c9eff --- /dev/null +++ b/Qwen3-ASR-1.7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33bb28421a3bf976eff8f65b5871946e88c0bcad479a46be9539b8fae521f51a +size 1181583840 diff --git a/Qwen3-ASR-1.7B.Q2_K.gguf b/Qwen3-ASR-1.7B.Q2_K.gguf new file mode 100644 index 0000000..df46f17 --- /dev/null +++ b/Qwen3-ASR-1.7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7179b5510c144a0fd841bb8c0a8aa622df72fe806818ac663b4642afbd70553f +size 879892960 diff --git a/Qwen3-ASR-1.7B.Q3_K_L.gguf b/Qwen3-ASR-1.7B.Q3_K_L.gguf new file mode 100644 index 0000000..20a07e6 --- /dev/null +++ b/Qwen3-ASR-1.7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f0ff4b020d7443bb6516d6fa4642652df82709b3581500286494faba121a2b7 +size 1137201632 diff --git a/Qwen3-ASR-1.7B.Q3_K_M.gguf b/Qwen3-ASR-1.7B.Q3_K_M.gguf new file mode 100644 index 0000000..2ab0df6 --- /dev/null +++ b/Qwen3-ASR-1.7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfbf333c73c9ac8769733997c1bd63c35236dbe7531e8213c3337f842dec4728 +size 1073238496 diff --git a/Qwen3-ASR-1.7B.Q3_K_S.gguf b/Qwen3-ASR-1.7B.Q3_K_S.gguf new file mode 100644 index 0000000..5bfcf56 --- /dev/null +++ b/Qwen3-ASR-1.7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18e94ae46c2fdbf602e33d0263e15b6a2cba6aa3b83cab3f0d95c45b01012d15 +size 1000952288 diff --git a/Qwen3-ASR-1.7B.Q4_K_M.gguf b/Qwen3-ASR-1.7B.Q4_K_M.gguf new file mode 100644 index 0000000..23480d9 --- /dev/null +++ b/Qwen3-ASR-1.7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3893b8926065bbff3da7586d21d8711a9b4fa4fa8f12cd0cefad58e31b2660b6 +size 1282435552 diff --git a/Qwen3-ASR-1.7B.Q4_K_S.gguf b/Qwen3-ASR-1.7B.Q4_K_S.gguf new file mode 100644 index 0000000..1a4454e --- /dev/null +++ b/Qwen3-ASR-1.7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cde242213aad6abf2ac1c671ad03a00bd197c01a990a8fab2f9d0bd8831cb5f +size 1235216864 diff --git a/Qwen3-ASR-1.7B.Q5_K_M.gguf b/Qwen3-ASR-1.7B.Q5_K_M.gguf new file mode 100644 index 0000000..cc8195c --- /dev/null +++ b/Qwen3-ASR-1.7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61ee49cb2dbf37d49ad9413661f8ee3e715ce14ba775b3f8dc528fa682cbe606 +size 1471801824 diff --git a/Qwen3-ASR-1.7B.Q5_K_S.gguf b/Qwen3-ASR-1.7B.Q5_K_S.gguf new file mode 100644 index 0000000..05293de --- /dev/null +++ b/Qwen3-ASR-1.7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0d06001de72309518270ecc377a977b14818b14d815fa015a7e3333fff43a30 +size 1444506080 diff --git a/Qwen3-ASR-1.7B.Q6_K.gguf b/Qwen3-ASR-1.7B.Q6_K.gguf new file mode 100644 index 0000000..1012c83 --- /dev/null +++ b/Qwen3-ASR-1.7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:534b653ee0074264c80533df9637e9eb556c04457f30cd1ba08fe48dcb608263 +size 1673003488 diff --git a/Qwen3-ASR-1.7B.Q8_0.gguf b/Qwen3-ASR-1.7B.Q8_0.gguf new file mode 100644 index 0000000..ff395e7 --- /dev/null +++ b/Qwen3-ASR-1.7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49eefdfad5b5b272220d150ca0cd2ca1734fe2e3651c412ea686e35299f4d7d7 +size 2165035488 diff --git a/Qwen3-ASR-1.7B.f16.gguf b/Qwen3-ASR-1.7B.f16.gguf new file mode 100644 index 0000000..bad9dde --- /dev/null +++ b/Qwen3-ASR-1.7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b97b1d6b7a8b882314916d364dd0b0650e1683491a974f0c3719cfe8cf8901f +size 4069675488 diff --git a/Qwen3-ASR-1.7B.mmproj-Q8_0.gguf b/Qwen3-ASR-1.7B.mmproj-Q8_0.gguf new file mode 100644 index 0000000..c6eb637 --- /dev/null +++ b/Qwen3-ASR-1.7B.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:780b5b48dfbc23c219cc9d3da9fdaccc7da567fa661b3724d19bda50fbcfc8c3 +size 355709472 diff --git a/Qwen3-ASR-1.7B.mmproj-f16.gguf b/Qwen3-ASR-1.7B.mmproj-f16.gguf new file mode 100644 index 0000000..64720e8 --- /dev/null +++ b/Qwen3-ASR-1.7B.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bc361e19bfdf3617c85247f9b706f7186ce0d156d9ed3c5d8bca8900b8fc3b7 +size 641774112 diff --git a/README.md b/README.md new file mode 100644 index 0000000..bd928a6 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: Qwen/Qwen3-ASR-1.7B +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Qwen/Qwen3-ASR-1.7B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-ASR-1.7B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-ASR-1.7B-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-ASR-1.7B-GGUF/resolve/main/Qwen3-ASR-1.7B.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.5 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-ASR-1.7B-GGUF/resolve/main/Qwen3-ASR-1.7B.mmproj-f16.gguf) | mmproj-f16 | 0.7 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-ASR-1.7B-GGUF/resolve/main/Qwen3-ASR-1.7B.Q2_K.gguf) | Q2_K | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-ASR-1.7B-GGUF/resolve/main/Qwen3-ASR-1.7B.Q3_K_S.gguf) | Q3_K_S | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-ASR-1.7B-GGUF/resolve/main/Qwen3-ASR-1.7B.Q3_K_M.gguf) | Q3_K_M | 1.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-ASR-1.7B-GGUF/resolve/main/Qwen3-ASR-1.7B.Q3_K_L.gguf) | Q3_K_L | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-ASR-1.7B-GGUF/resolve/main/Qwen3-ASR-1.7B.IQ4_XS.gguf) | IQ4_XS | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-ASR-1.7B-GGUF/resolve/main/Qwen3-ASR-1.7B.Q4_K_S.gguf) | Q4_K_S | 1.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-ASR-1.7B-GGUF/resolve/main/Qwen3-ASR-1.7B.Q4_K_M.gguf) | Q4_K_M | 1.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-ASR-1.7B-GGUF/resolve/main/Qwen3-ASR-1.7B.Q5_K_S.gguf) | Q5_K_S | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-ASR-1.7B-GGUF/resolve/main/Qwen3-ASR-1.7B.Q5_K_M.gguf) | Q5_K_M | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-ASR-1.7B-GGUF/resolve/main/Qwen3-ASR-1.7B.Q6_K.gguf) | Q6_K | 1.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-ASR-1.7B-GGUF/resolve/main/Qwen3-ASR-1.7B.Q8_0.gguf) | Q8_0 | 2.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-ASR-1.7B-GGUF/resolve/main/Qwen3-ASR-1.7B.f16.gguf) | f16 | 4.2 | 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. + +