commit 7e4b8f8bd40e8e5482978cc1bd1d93c61001d416 Author: ModelHub XC Date: Thu Jul 23 22:38:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-R1984-4B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..26bca69 --- /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-R1984-4B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-R1984-4B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-R1984-4B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-R1984-4B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-R1984-4B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-R1984-4B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-R1984-4B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-R1984-4B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-R1984-4B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-R1984-4B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-R1984-4B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-R1984-4B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-R1984-4B.IQ4_XS.gguf b/Qwen3-R1984-4B.IQ4_XS.gguf new file mode 100644 index 0000000..8acd51e --- /dev/null +++ b/Qwen3-R1984-4B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87b36543da2ab6677e96b84e50bee62b3f59e4dea33dcd94c1019a833214c7bb +size 2286316224 diff --git a/Qwen3-R1984-4B.Q2_K.gguf b/Qwen3-R1984-4B.Q2_K.gguf new file mode 100644 index 0000000..34df1a1 --- /dev/null +++ b/Qwen3-R1984-4B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c9baf4b344c83b75f7a4cff895294fd0cfdc8fe12c3f39bbce12bd9154895f4 +size 1669499584 diff --git a/Qwen3-R1984-4B.Q3_K_L.gguf b/Qwen3-R1984-4B.Q3_K_L.gguf new file mode 100644 index 0000000..47157f9 --- /dev/null +++ b/Qwen3-R1984-4B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c2bddfd64f5c1dc6f413f7a25c305842f32810e9aa94ab0a5ed5c566419b68d +size 2239785664 diff --git a/Qwen3-R1984-4B.Q3_K_M.gguf b/Qwen3-R1984-4B.Q3_K_M.gguf new file mode 100644 index 0000000..92765d7 --- /dev/null +++ b/Qwen3-R1984-4B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59a9dbb5ee1680787e62f9cc28097f9dc32100d147b59d56a24c40bc73cd71ea +size 2075617984 diff --git a/Qwen3-R1984-4B.Q3_K_S.gguf b/Qwen3-R1984-4B.Q3_K_S.gguf new file mode 100644 index 0000000..5b20a47 --- /dev/null +++ b/Qwen3-R1984-4B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0954844331e67d73647ee888b8bf2e3b7a1038395b85a33cc173d3ee4c28b4b6 +size 1886997184 diff --git a/Qwen3-R1984-4B.Q4_K_M.gguf b/Qwen3-R1984-4B.Q4_K_M.gguf new file mode 100644 index 0000000..55ec316 --- /dev/null +++ b/Qwen3-R1984-4B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06bdbb5cfb19cb2cbd9d8d434a4565492107e8b11d9308dda4d06fdfb9d5f0fe +size 2497280704 diff --git a/Qwen3-R1984-4B.Q4_K_S.gguf b/Qwen3-R1984-4B.Q4_K_S.gguf new file mode 100644 index 0000000..602bff5 --- /dev/null +++ b/Qwen3-R1984-4B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d02b1d9d57aab2113dc8c957e1f391e00f762002bb28bfb75d142e7f03ad8562 +size 2383309504 diff --git a/Qwen3-R1984-4B.Q5_K_M.gguf b/Qwen3-R1984-4B.Q5_K_M.gguf new file mode 100644 index 0000000..724d5ac --- /dev/null +++ b/Qwen3-R1984-4B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2b74f8a6f7042b8d4a1aeae5062aaf21cc280e8c0883c356a953f37c2e28596 +size 2889513664 diff --git a/Qwen3-R1984-4B.Q5_K_S.gguf b/Qwen3-R1984-4B.Q5_K_S.gguf new file mode 100644 index 0000000..f18cf73 --- /dev/null +++ b/Qwen3-R1984-4B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21ab0f7c81c93dd32984e5c7669656067743dc0b88fc794c04a11d22ff37b628 +size 2823711424 diff --git a/Qwen3-R1984-4B.Q6_K.gguf b/Qwen3-R1984-4B.Q6_K.gguf new file mode 100644 index 0000000..d1af29b --- /dev/null +++ b/Qwen3-R1984-4B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c4afb15cb156c2d8befa615e1c8f8b33c9ac16ced94c8bcb9b28be891987816 +size 3306261184 diff --git a/Qwen3-R1984-4B.Q8_0.gguf b/Qwen3-R1984-4B.Q8_0.gguf new file mode 100644 index 0000000..57fbe46 --- /dev/null +++ b/Qwen3-R1984-4B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f54047ff64a8cb71b4c4dd59694c561a7af4b212d05f47949a0ccd34e96ef974 +size 4280405184 diff --git a/Qwen3-R1984-4B.f16.gguf b/Qwen3-R1984-4B.f16.gguf new file mode 100644 index 0000000..b0a46ec --- /dev/null +++ b/Qwen3-R1984-4B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be764f8eb0df02f7fa1152bf43fc89f9f5ca02562af4084f956d6f7158e3cdf5 +size 8051285184 diff --git a/README.md b/README.md new file mode 100644 index 0000000..633845f --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: VIDraft/Qwen3-R1984-4B +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/VIDraft/Qwen3-R1984-4B + + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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-R1984-4B-GGUF/resolve/main/Qwen3-R1984-4B.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-R1984-4B-GGUF/resolve/main/Qwen3-R1984-4B.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-R1984-4B-GGUF/resolve/main/Qwen3-R1984-4B.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-R1984-4B-GGUF/resolve/main/Qwen3-R1984-4B.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-R1984-4B-GGUF/resolve/main/Qwen3-R1984-4B.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-R1984-4B-GGUF/resolve/main/Qwen3-R1984-4B.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-R1984-4B-GGUF/resolve/main/Qwen3-R1984-4B.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-R1984-4B-GGUF/resolve/main/Qwen3-R1984-4B.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-R1984-4B-GGUF/resolve/main/Qwen3-R1984-4B.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-R1984-4B-GGUF/resolve/main/Qwen3-R1984-4B.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-R1984-4B-GGUF/resolve/main/Qwen3-R1984-4B.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-R1984-4B-GGUF/resolve/main/Qwen3-R1984-4B.f16.gguf) | f16 | 8.2 | 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. + +