commit 953ee9f8b753ae19181462a505b84a082823b424 Author: ModelHub XC Date: Fri Jul 17 18:42:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7eac851 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,59 @@ +*.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 +Qwen2.5-7B.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B.IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B.Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B.Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B.SOURCE.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-7B.IQ3_M.gguf b/Qwen2.5-7B.IQ3_M.gguf new file mode 100644 index 0000000..d0c0b08 --- /dev/null +++ b/Qwen2.5-7B.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2981a13ad1a18e0f9639432f7a4bb6d7fa2cb5ec4d432ed9dc87f4a18218d88 +size 3574012352 diff --git a/Qwen2.5-7B.IQ3_S.gguf b/Qwen2.5-7B.IQ3_S.gguf new file mode 100644 index 0000000..c2e6f60 --- /dev/null +++ b/Qwen2.5-7B.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:035e992fcce7bfab675fe3324ee042f0a9c7a803e72780604904877976c179bd +size 3499192768 diff --git a/Qwen2.5-7B.IQ3_XS.gguf b/Qwen2.5-7B.IQ3_XS.gguf new file mode 100644 index 0000000..555feb3 --- /dev/null +++ b/Qwen2.5-7B.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ef9684c4225ae352a0b520bc6834417bfac40cc039611de1ecc3c882eaba7b0 +size 3346256320 diff --git a/Qwen2.5-7B.IQ4_NL.gguf b/Qwen2.5-7B.IQ4_NL.gguf new file mode 100644 index 0000000..1331d3f --- /dev/null +++ b/Qwen2.5-7B.IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0371886b0d349c495695003fac0480bece81c430fb0975762a75743914c8d193 +size 4463274432 diff --git a/Qwen2.5-7B.IQ4_XS.gguf b/Qwen2.5-7B.IQ4_XS.gguf new file mode 100644 index 0000000..0112670 --- /dev/null +++ b/Qwen2.5-7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8e46825cabc7304431b76fdcf5639f9a00e3572f3dd2f46c8360606b932f1cd +size 4250298816 diff --git a/Qwen2.5-7B.Q2_K.gguf b/Qwen2.5-7B.Q2_K.gguf new file mode 100644 index 0000000..412cb25 --- /dev/null +++ b/Qwen2.5-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb7dde0c6b480274be84594624ab4a329ef9cf5905894c4a2426fc4bc84f0bf9 +size 3015940544 diff --git a/Qwen2.5-7B.Q3_K_L.gguf b/Qwen2.5-7B.Q3_K_L.gguf new file mode 100644 index 0000000..a2ae792 --- /dev/null +++ b/Qwen2.5-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a5a843a14b57629014967707cbf8f85972433c8a62a5b7fda631d60428b32d8 +size 4088459712 diff --git a/Qwen2.5-7B.Q3_K_M.gguf b/Qwen2.5-7B.Q3_K_M.gguf new file mode 100644 index 0000000..bba4894 --- /dev/null +++ b/Qwen2.5-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7243fcc2342c8a4ef11dbb8061c34de6e4338d35f295f9af34d7ce79e7b2d3c3 +size 3808391616 diff --git a/Qwen2.5-7B.Q3_K_S.gguf b/Qwen2.5-7B.Q3_K_S.gguf new file mode 100644 index 0000000..09e5f3e --- /dev/null +++ b/Qwen2.5-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2aa23cf512f87416eb537b42a928fcbfe0ddd1a8600ac4efd49948b32abbfb9b +size 3492368832 diff --git a/Qwen2.5-7B.Q4_0.gguf b/Qwen2.5-7B.Q4_0.gguf new file mode 100644 index 0000000..a430f14 --- /dev/null +++ b/Qwen2.5-7B.Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f56a0ebd3267c4a29df933247c154eb639cf53ed94692d1283a25a6a63e7fc78 +size 4431391168 diff --git a/Qwen2.5-7B.Q4_0_4_4.gguf b/Qwen2.5-7B.Q4_0_4_4.gguf new file mode 100644 index 0000000..25fe50d --- /dev/null +++ b/Qwen2.5-7B.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a78085a96cc91a799c74be3cc444da63308b23cfd154a850f374d8527e4b6da0 +size 4431391168 diff --git a/Qwen2.5-7B.Q4_0_4_8.gguf b/Qwen2.5-7B.Q4_0_4_8.gguf new file mode 100644 index 0000000..41562df --- /dev/null +++ b/Qwen2.5-7B.Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4dc527cf297767a5919e29aca31903d3b0bfe93e4dab327dae013c8c1ffdc09 +size 4431391168 diff --git a/Qwen2.5-7B.Q4_0_8_8.gguf b/Qwen2.5-7B.Q4_0_8_8.gguf new file mode 100644 index 0000000..6a0805a --- /dev/null +++ b/Qwen2.5-7B.Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fa35f076e5c7090f92ac88a8cee398034666a2caf7d96d548b44b5d51146cb3 +size 4431391168 diff --git a/Qwen2.5-7B.Q4_1.gguf b/Qwen2.5-7B.Q4_1.gguf new file mode 100644 index 0000000..b9a24ef --- /dev/null +++ b/Qwen2.5-7B.Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6118743df0841cdc6bfc5c40da8468b3d8d78cbd69bb45332cb4ad33c739102 +size 4873284032 diff --git a/Qwen2.5-7B.Q4_K_M.gguf b/Qwen2.5-7B.Q4_K_M.gguf new file mode 100644 index 0000000..e2ade58 --- /dev/null +++ b/Qwen2.5-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1c8899139b014b35d0b205e99319a8de73cf122c615b5cb0d2cd28c8a97b4d2 +size 4683073984 diff --git a/Qwen2.5-7B.Q4_K_S.gguf b/Qwen2.5-7B.Q4_K_S.gguf new file mode 100644 index 0000000..3a72e3b --- /dev/null +++ b/Qwen2.5-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f40f297bf2737f856e1edb3c4fb262ad6ca3582ac88feed92e3ac3bf19ded92f +size 4457769408 diff --git a/Qwen2.5-7B.Q5_0.gguf b/Qwen2.5-7B.Q5_0.gguf new file mode 100644 index 0000000..8d3f3de --- /dev/null +++ b/Qwen2.5-7B.Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:536046bb8bc83012580675216d386031e937a713e5ae4eac0f939d30923d308b +size 5315176896 diff --git a/Qwen2.5-7B.Q5_1.gguf b/Qwen2.5-7B.Q5_1.gguf new file mode 100644 index 0000000..d1059c3 --- /dev/null +++ b/Qwen2.5-7B.Q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1131528c614f6f59e5acea251cf5c5c1a9294fe5e342ed10b1b2638f4b1f98a6 +size 5757069760 diff --git a/Qwen2.5-7B.Q5_K_M.gguf b/Qwen2.5-7B.Q5_K_M.gguf new file mode 100644 index 0000000..3adebac --- /dev/null +++ b/Qwen2.5-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b1e4482decdbf6671453ffd1d26123d43b4429c5a20b551543865a083cfdc8d +size 5444831680 diff --git a/Qwen2.5-7B.Q5_K_S.gguf b/Qwen2.5-7B.Q5_K_S.gguf new file mode 100644 index 0000000..7353ed5 --- /dev/null +++ b/Qwen2.5-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e97fba4d6abfd8c83c5c945082ba407d080ac1445eea5d6b589c46d73491d02b +size 5315176896 diff --git a/Qwen2.5-7B.Q6_K.gguf b/Qwen2.5-7B.Q6_K.gguf new file mode 100644 index 0000000..09e4ed0 --- /dev/null +++ b/Qwen2.5-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2463225d86f895eaa69956f3271703f91362b9f68b904cf926d51ad4942d502a +size 6254199232 diff --git a/Qwen2.5-7B.Q8_0.gguf b/Qwen2.5-7B.Q8_0.gguf new file mode 100644 index 0000000..3106149 --- /dev/null +++ b/Qwen2.5-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2e888849762f7be3a76176deb8beca27a16aada54f7e52970ec3b1822ca8ef8 +size 8098525632 diff --git a/Qwen2.5-7B.SOURCE.gguf b/Qwen2.5-7B.SOURCE.gguf new file mode 100644 index 0000000..a0404bf --- /dev/null +++ b/Qwen2.5-7B.SOURCE.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8018c31d204ce376a02005a9882b9a61c3ba6ae6c4860026736fbf43c80d0d2 +size 15237853216 diff --git a/Qwen2.5-7B.f16.gguf b/Qwen2.5-7B.f16.gguf new file mode 100644 index 0000000..7ecbe5d --- /dev/null +++ b/Qwen2.5-7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c241b6ccb6d33445d956a5cac6fa773947234ecf695bebd532fa86e6226d4a6 +size 15237853632 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d228a5a --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: Qwen/Qwen2.5-7B +language: +- en +library_name: transformers +license: apache-2.0 +license_link: https://huggingface.co/Qwen/Qwen2.5-7B/blob/main/LICENSE +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Qwen/Qwen2.5-7B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2.5-7B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen2.5-7B-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/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.IQ3_XS.gguf) | IQ3_XS | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.IQ3_S.gguf) | IQ3_S | 3.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.IQ3_M.gguf) | IQ3_M | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.Q4_0.gguf) | Q4_0 | 4.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.5 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.Q4_0_4_8.gguf) | Q4_0_4_8 | 4.5 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.Q4_0_8_8.gguf) | Q4_0_8_8 | 4.5 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.IQ4_NL.gguf) | IQ4_NL | 4.6 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.Q4_1.gguf) | Q4_1 | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.Q5_0.gguf) | Q5_0 | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.Q5_1.gguf) | Q5_1 | 5.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.SOURCE.gguf) | SOURCE | 15.3 | source gguf, only provided when it was hard to come by | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.f16.gguf) | f16 | 15.3 | 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. + +