commit c87dce7387a2b85522aa27494593af26cd937a46 Author: ModelHub XC Date: Tue May 26 22:25:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen25-7B-Inst-Tulu-35k-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..95b02fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.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 +Qwen25-7B-Inst-Tulu-35k.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Qwen25-7B-Inst-Tulu-35k.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen25-7B-Inst-Tulu-35k.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen25-7B-Inst-Tulu-35k.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen25-7B-Inst-Tulu-35k.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen25-7B-Inst-Tulu-35k.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen25-7B-Inst-Tulu-35k.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen25-7B-Inst-Tulu-35k.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen25-7B-Inst-Tulu-35k.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen25-7B-Inst-Tulu-35k.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen25-7B-Inst-Tulu-35k.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen25-7B-Inst-Tulu-35k.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen25-7B-Inst-Tulu-35k.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen25-7B-Inst-Tulu-35k.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen25-7B-Inst-Tulu-35k.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen25-7B-Inst-Tulu-35k.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen25-7B-Inst-Tulu-35k.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen25-7B-Inst-Tulu-35k.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen25-7B-Inst-Tulu-35k.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen25-7B-Inst-Tulu-35k.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen25-7B-Inst-Tulu-35k.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen25-7B-Inst-Tulu-35k.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen25-7B-Inst-Tulu-35k.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen25-7B-Inst-Tulu-35k.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen25-7B-Inst-Tulu-35k.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen25-7B-Inst-Tulu-35k.i1-IQ1_M.gguf b/Qwen25-7B-Inst-Tulu-35k.i1-IQ1_M.gguf new file mode 100644 index 0000000..862d51f --- /dev/null +++ b/Qwen25-7B-Inst-Tulu-35k.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ae678a7698b71d8e108c32b38b0fd07e042259b13b26c58fe555f043a4d9aef +size 2042197120 diff --git a/Qwen25-7B-Inst-Tulu-35k.i1-IQ1_S.gguf b/Qwen25-7B-Inst-Tulu-35k.i1-IQ1_S.gguf new file mode 100644 index 0000000..163d8ef --- /dev/null +++ b/Qwen25-7B-Inst-Tulu-35k.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b5f0fa3efc9983a5e0a52e3d8032eec0d855332acf37863d1f69bd17c5752ce +size 1903668352 diff --git a/Qwen25-7B-Inst-Tulu-35k.i1-IQ2_M.gguf b/Qwen25-7B-Inst-Tulu-35k.i1-IQ2_M.gguf new file mode 100644 index 0000000..c42b3d3 --- /dev/null +++ b/Qwen25-7B-Inst-Tulu-35k.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a6273b964611f270942718c91b2352efabfd5f7b6205423dc4d268af4ccff34 +size 2780343424 diff --git a/Qwen25-7B-Inst-Tulu-35k.i1-IQ2_S.gguf b/Qwen25-7B-Inst-Tulu-35k.i1-IQ2_S.gguf new file mode 100644 index 0000000..9ac7dcd --- /dev/null +++ b/Qwen25-7B-Inst-Tulu-35k.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:074a10c6194440befc70ceb78006ed61af7b135285bbf1d811d6b5168aff2636 +size 2595638400 diff --git a/Qwen25-7B-Inst-Tulu-35k.i1-IQ2_XS.gguf b/Qwen25-7B-Inst-Tulu-35k.i1-IQ2_XS.gguf new file mode 100644 index 0000000..1f60fc9 --- /dev/null +++ b/Qwen25-7B-Inst-Tulu-35k.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4eab0c0d37dc3d4db74a0eaebdfb98eaf5818b3676a81dca81855523a08db7e4 +size 2469022848 diff --git a/Qwen25-7B-Inst-Tulu-35k.i1-IQ2_XXS.gguf b/Qwen25-7B-Inst-Tulu-35k.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..4020035 --- /dev/null +++ b/Qwen25-7B-Inst-Tulu-35k.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef1bd1d8c35c71804806c77d4b48846025aa962b6fd0d5387d2e22d067450c28 +size 2273078400 diff --git a/Qwen25-7B-Inst-Tulu-35k.i1-IQ3_M.gguf b/Qwen25-7B-Inst-Tulu-35k.i1-IQ3_M.gguf new file mode 100644 index 0000000..41e5f5f --- /dev/null +++ b/Qwen25-7B-Inst-Tulu-35k.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03fef748f41e8addffa5282be9f86bdd8e9aca1ea543ae859793ed73aa619e3c +size 3574013056 diff --git a/Qwen25-7B-Inst-Tulu-35k.i1-IQ3_S.gguf b/Qwen25-7B-Inst-Tulu-35k.i1-IQ3_S.gguf new file mode 100644 index 0000000..435effd --- /dev/null +++ b/Qwen25-7B-Inst-Tulu-35k.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbc55f778d2f6e7b8045e846534f43600cb66a24d5a65aff0d0cbf1f73050e80 +size 3499193472 diff --git a/Qwen25-7B-Inst-Tulu-35k.i1-IQ3_XS.gguf b/Qwen25-7B-Inst-Tulu-35k.i1-IQ3_XS.gguf new file mode 100644 index 0000000..177f574 --- /dev/null +++ b/Qwen25-7B-Inst-Tulu-35k.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:026293cc4502957c4dab60b2f8446e27e5277165907ef2566d2bd9168ded3762 +size 3346257024 diff --git a/Qwen25-7B-Inst-Tulu-35k.i1-IQ3_XXS.gguf b/Qwen25-7B-Inst-Tulu-35k.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..2fef218 --- /dev/null +++ b/Qwen25-7B-Inst-Tulu-35k.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9c391c9c360814a7cb4c5430490dc93abd5cb5b013b89f0007fff07674a0f2c +size 3114515584 diff --git a/Qwen25-7B-Inst-Tulu-35k.i1-IQ4_NL.gguf b/Qwen25-7B-Inst-Tulu-35k.i1-IQ4_NL.gguf new file mode 100644 index 0000000..3abb5a1 --- /dev/null +++ b/Qwen25-7B-Inst-Tulu-35k.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:824141b77b0280c44df1d64938e911216a5838f9725ddc092d2d8d371d5a02e5 +size 4437814400 diff --git a/Qwen25-7B-Inst-Tulu-35k.i1-IQ4_XS.gguf b/Qwen25-7B-Inst-Tulu-35k.i1-IQ4_XS.gguf new file mode 100644 index 0000000..6768ad1 --- /dev/null +++ b/Qwen25-7B-Inst-Tulu-35k.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1029e139e7a97b960152fe38db7325a40e04ff9468bc7dd1b56133402ede92ca +size 4218473600 diff --git a/Qwen25-7B-Inst-Tulu-35k.i1-Q2_K.gguf b/Qwen25-7B-Inst-Tulu-35k.i1-Q2_K.gguf new file mode 100644 index 0000000..bd72da5 --- /dev/null +++ b/Qwen25-7B-Inst-Tulu-35k.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c036e19a5b5a6e949fe4a5858fb18a59a4850702284cdd88c1601d791359028 +size 3015941248 diff --git a/Qwen25-7B-Inst-Tulu-35k.i1-Q2_K_S.gguf b/Qwen25-7B-Inst-Tulu-35k.i1-Q2_K_S.gguf new file mode 100644 index 0000000..10ea7ab --- /dev/null +++ b/Qwen25-7B-Inst-Tulu-35k.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ac0259d46bc6f6970c0dfe9b50dafbee64801f329429fa350188a002d2dee9d +size 2834074752 diff --git a/Qwen25-7B-Inst-Tulu-35k.i1-Q3_K_L.gguf b/Qwen25-7B-Inst-Tulu-35k.i1-Q3_K_L.gguf new file mode 100644 index 0000000..2e32b1e --- /dev/null +++ b/Qwen25-7B-Inst-Tulu-35k.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a436d131568b836b1bcea82c8dde863c252d1830f23af3496e773737c7179eb +size 4088460416 diff --git a/Qwen25-7B-Inst-Tulu-35k.i1-Q3_K_M.gguf b/Qwen25-7B-Inst-Tulu-35k.i1-Q3_K_M.gguf new file mode 100644 index 0000000..a891ba9 --- /dev/null +++ b/Qwen25-7B-Inst-Tulu-35k.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7c7643a45db49ab22fc33ade9654a85247855985279c269a3abed6beab5b57b +size 3808392320 diff --git a/Qwen25-7B-Inst-Tulu-35k.i1-Q3_K_S.gguf b/Qwen25-7B-Inst-Tulu-35k.i1-Q3_K_S.gguf new file mode 100644 index 0000000..8dc1bea --- /dev/null +++ b/Qwen25-7B-Inst-Tulu-35k.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05bc27803f76fe6b06ca08a24ae0cecf572bed4e8b522306e1f3480c3bbef9fc +size 3492369536 diff --git a/Qwen25-7B-Inst-Tulu-35k.i1-Q4_0.gguf b/Qwen25-7B-Inst-Tulu-35k.i1-Q4_0.gguf new file mode 100644 index 0000000..3bbe7a9 --- /dev/null +++ b/Qwen25-7B-Inst-Tulu-35k.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:961ed2a18243671a9aa77e85ad393d3a06669742ec508bedb905d638aca3879a +size 4444122240 diff --git a/Qwen25-7B-Inst-Tulu-35k.i1-Q4_1.gguf b/Qwen25-7B-Inst-Tulu-35k.i1-Q4_1.gguf new file mode 100644 index 0000000..c8219d2 --- /dev/null +++ b/Qwen25-7B-Inst-Tulu-35k.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4f180d8123e5ec3dd49c169344dec76162e13a3d010b7c76f5b9d9292c41186 +size 4873284736 diff --git a/Qwen25-7B-Inst-Tulu-35k.i1-Q4_K_M.gguf b/Qwen25-7B-Inst-Tulu-35k.i1-Q4_K_M.gguf new file mode 100644 index 0000000..65258a8 --- /dev/null +++ b/Qwen25-7B-Inst-Tulu-35k.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60f0d7f02001dc2c8ba16ecafc9281fc555a79b189e3673e77c697171a851248 +size 4683074688 diff --git a/Qwen25-7B-Inst-Tulu-35k.i1-Q4_K_S.gguf b/Qwen25-7B-Inst-Tulu-35k.i1-Q4_K_S.gguf new file mode 100644 index 0000000..af660ff --- /dev/null +++ b/Qwen25-7B-Inst-Tulu-35k.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d19a023e137f3cf81fed399b441da828b6a72b4c3577f13a8cd00720d283b1d9 +size 4457770112 diff --git a/Qwen25-7B-Inst-Tulu-35k.i1-Q5_K_M.gguf b/Qwen25-7B-Inst-Tulu-35k.i1-Q5_K_M.gguf new file mode 100644 index 0000000..385b817 --- /dev/null +++ b/Qwen25-7B-Inst-Tulu-35k.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e932270641d4d9fd5ef4a3d561ac825cc63ebc78ffeeec5d99bbac2fcf53cba +size 5444832384 diff --git a/Qwen25-7B-Inst-Tulu-35k.i1-Q5_K_S.gguf b/Qwen25-7B-Inst-Tulu-35k.i1-Q5_K_S.gguf new file mode 100644 index 0000000..fe96c1e --- /dev/null +++ b/Qwen25-7B-Inst-Tulu-35k.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7cd987beb6c6e0cccfad713a98bc76cfc9acf20e62bcf253ace8cbbc77f15ed +size 5315177600 diff --git a/Qwen25-7B-Inst-Tulu-35k.i1-Q6_K.gguf b/Qwen25-7B-Inst-Tulu-35k.i1-Q6_K.gguf new file mode 100644 index 0000000..71491b9 --- /dev/null +++ b/Qwen25-7B-Inst-Tulu-35k.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6671437bd6d106171a59062c791c7972062131ec105eaf73ced2c509b50604ae +size 6254199936 diff --git a/Qwen25-7B-Inst-Tulu-35k.imatrix.gguf b/Qwen25-7B-Inst-Tulu-35k.imatrix.gguf new file mode 100644 index 0000000..0489c5e --- /dev/null +++ b/Qwen25-7B-Inst-Tulu-35k.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:397e4c1e10ea0594deb50e677e58a5cee8a5fbe0ab84207f0865d1f7a577e48b +size 4560352 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f0962c5 --- /dev/null +++ b/README.md @@ -0,0 +1,88 @@ +--- +base_model: Silin1590/Qwen25-7B-Inst-Tulu-35k +language: +- en +library_name: transformers +license: apache-2.0 +license_link: https://huggingface.co/Qwen/Qwen2.5-7B-Instruct/blob/main/LICENSE +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- chat +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/Silin1590/Qwen25-7B-Inst-Tulu-35k + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen25-7B-Inst-Tulu-35k-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Qwen25-7B-Inst-Tulu-35k-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/Qwen25-7B-Inst-Tulu-35k-i1-GGUF/resolve/main/Qwen25-7B-Inst-Tulu-35k.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Qwen25-7B-Inst-Tulu-35k-i1-GGUF/resolve/main/Qwen25-7B-Inst-Tulu-35k.i1-IQ1_S.gguf) | i1-IQ1_S | 2.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen25-7B-Inst-Tulu-35k-i1-GGUF/resolve/main/Qwen25-7B-Inst-Tulu-35k.i1-IQ1_M.gguf) | i1-IQ1_M | 2.1 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen25-7B-Inst-Tulu-35k-i1-GGUF/resolve/main/Qwen25-7B-Inst-Tulu-35k.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen25-7B-Inst-Tulu-35k-i1-GGUF/resolve/main/Qwen25-7B-Inst-Tulu-35k.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen25-7B-Inst-Tulu-35k-i1-GGUF/resolve/main/Qwen25-7B-Inst-Tulu-35k.i1-IQ2_S.gguf) | i1-IQ2_S | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen25-7B-Inst-Tulu-35k-i1-GGUF/resolve/main/Qwen25-7B-Inst-Tulu-35k.i1-IQ2_M.gguf) | i1-IQ2_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen25-7B-Inst-Tulu-35k-i1-GGUF/resolve/main/Qwen25-7B-Inst-Tulu-35k.i1-Q2_K_S.gguf) | i1-Q2_K_S | 2.9 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen25-7B-Inst-Tulu-35k-i1-GGUF/resolve/main/Qwen25-7B-Inst-Tulu-35k.i1-Q2_K.gguf) | i1-Q2_K | 3.1 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen25-7B-Inst-Tulu-35k-i1-GGUF/resolve/main/Qwen25-7B-Inst-Tulu-35k.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen25-7B-Inst-Tulu-35k-i1-GGUF/resolve/main/Qwen25-7B-Inst-Tulu-35k.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen25-7B-Inst-Tulu-35k-i1-GGUF/resolve/main/Qwen25-7B-Inst-Tulu-35k.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen25-7B-Inst-Tulu-35k-i1-GGUF/resolve/main/Qwen25-7B-Inst-Tulu-35k.i1-IQ3_S.gguf) | i1-IQ3_S | 3.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen25-7B-Inst-Tulu-35k-i1-GGUF/resolve/main/Qwen25-7B-Inst-Tulu-35k.i1-IQ3_M.gguf) | i1-IQ3_M | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen25-7B-Inst-Tulu-35k-i1-GGUF/resolve/main/Qwen25-7B-Inst-Tulu-35k.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.9 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen25-7B-Inst-Tulu-35k-i1-GGUF/resolve/main/Qwen25-7B-Inst-Tulu-35k.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.2 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen25-7B-Inst-Tulu-35k-i1-GGUF/resolve/main/Qwen25-7B-Inst-Tulu-35k.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen25-7B-Inst-Tulu-35k-i1-GGUF/resolve/main/Qwen25-7B-Inst-Tulu-35k.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Qwen25-7B-Inst-Tulu-35k-i1-GGUF/resolve/main/Qwen25-7B-Inst-Tulu-35k.i1-Q4_0.gguf) | i1-Q4_0 | 4.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen25-7B-Inst-Tulu-35k-i1-GGUF/resolve/main/Qwen25-7B-Inst-Tulu-35k.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.6 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen25-7B-Inst-Tulu-35k-i1-GGUF/resolve/main/Qwen25-7B-Inst-Tulu-35k.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen25-7B-Inst-Tulu-35k-i1-GGUF/resolve/main/Qwen25-7B-Inst-Tulu-35k.i1-Q4_1.gguf) | i1-Q4_1 | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen25-7B-Inst-Tulu-35k-i1-GGUF/resolve/main/Qwen25-7B-Inst-Tulu-35k.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen25-7B-Inst-Tulu-35k-i1-GGUF/resolve/main/Qwen25-7B-Inst-Tulu-35k.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen25-7B-Inst-Tulu-35k-i1-GGUF/resolve/main/Qwen25-7B-Inst-Tulu-35k.i1-Q6_K.gguf) | i1-Q6_K | 6.4 | practically like static Q6_K | + +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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +