commit d30d3324782fcaeaf5ca57e9998dd63b9a8a1bc9 Author: ModelHub XC Date: Thu May 28 02:10:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-4B-tau2-grpo-v0.1-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d21e4d3 --- /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 +Qwen3-4B-tau2-grpo-v0.1.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tau2-grpo-v0.1.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tau2-grpo-v0.1.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tau2-grpo-v0.1.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tau2-grpo-v0.1.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tau2-grpo-v0.1.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tau2-grpo-v0.1.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tau2-grpo-v0.1.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tau2-grpo-v0.1.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tau2-grpo-v0.1.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tau2-grpo-v0.1.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tau2-grpo-v0.1.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tau2-grpo-v0.1.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tau2-grpo-v0.1.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tau2-grpo-v0.1.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tau2-grpo-v0.1.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tau2-grpo-v0.1.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tau2-grpo-v0.1.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tau2-grpo-v0.1.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tau2-grpo-v0.1.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tau2-grpo-v0.1.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tau2-grpo-v0.1.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tau2-grpo-v0.1.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tau2-grpo-v0.1.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tau2-grpo-v0.1.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-4B-tau2-grpo-v0.1.i1-IQ1_M.gguf b/Qwen3-4B-tau2-grpo-v0.1.i1-IQ1_M.gguf new file mode 100644 index 0000000..18eeafa --- /dev/null +++ b/Qwen3-4B-tau2-grpo-v0.1.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f4d19d8e226c136e905cf2b128794487ed54679c0c0b7cff8a2752ef7cd7bfe +size 1127016832 diff --git a/Qwen3-4B-tau2-grpo-v0.1.i1-IQ1_S.gguf b/Qwen3-4B-tau2-grpo-v0.1.i1-IQ1_S.gguf new file mode 100644 index 0000000..4b57cc6 --- /dev/null +++ b/Qwen3-4B-tau2-grpo-v0.1.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a8faba69ac8bdedacfb44d66326df1a8633c0e08dbe35f8eaefce4f0e9f1f2d +size 1055254912 diff --git a/Qwen3-4B-tau2-grpo-v0.1.i1-IQ2_M.gguf b/Qwen3-4B-tau2-grpo-v0.1.i1-IQ2_M.gguf new file mode 100644 index 0000000..74de22e --- /dev/null +++ b/Qwen3-4B-tau2-grpo-v0.1.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34a723471b223629989e71087dc39d6073c0ad067ee2ef7d28ca4978c39750eb +size 1512982912 diff --git a/Qwen3-4B-tau2-grpo-v0.1.i1-IQ2_S.gguf b/Qwen3-4B-tau2-grpo-v0.1.i1-IQ2_S.gguf new file mode 100644 index 0000000..a5b58fa --- /dev/null +++ b/Qwen3-4B-tau2-grpo-v0.1.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cbb79dd02540256c33bbfebeaf32a0c53ab2ab71b34e83918de2a1c9c2473d4 +size 1417300352 diff --git a/Qwen3-4B-tau2-grpo-v0.1.i1-IQ2_XS.gguf b/Qwen3-4B-tau2-grpo-v0.1.i1-IQ2_XS.gguf new file mode 100644 index 0000000..6ed021b --- /dev/null +++ b/Qwen3-4B-tau2-grpo-v0.1.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1021280c745862fd4cc8b8c4dae84574335f3cf0017af2fee4665bb88c2be70 +size 1354099072 diff --git a/Qwen3-4B-tau2-grpo-v0.1.i1-IQ2_XXS.gguf b/Qwen3-4B-tau2-grpo-v0.1.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..c75849e --- /dev/null +++ b/Qwen3-4B-tau2-grpo-v0.1.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:132452a01dfa9daa73f31d92bb9c01f0504465d551ee997d853d8b7cb0709119 +size 1246620032 diff --git a/Qwen3-4B-tau2-grpo-v0.1.i1-IQ3_M.gguf b/Qwen3-4B-tau2-grpo-v0.1.i1-IQ3_M.gguf new file mode 100644 index 0000000..c47a6fa --- /dev/null +++ b/Qwen3-4B-tau2-grpo-v0.1.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8757e2031d9e4c307d25e359c87bc530d31d0fa78a6f336400458372d4e93df1 +size 1962895232 diff --git a/Qwen3-4B-tau2-grpo-v0.1.i1-IQ3_S.gguf b/Qwen3-4B-tau2-grpo-v0.1.i1-IQ3_S.gguf new file mode 100644 index 0000000..fc10200 --- /dev/null +++ b/Qwen3-4B-tau2-grpo-v0.1.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13eb791b34574bb65ff6701bf9503e2366924d24ac59212c779ffcadb8450761 +size 1899530112 diff --git a/Qwen3-4B-tau2-grpo-v0.1.i1-IQ3_XS.gguf b/Qwen3-4B-tau2-grpo-v0.1.i1-IQ3_XS.gguf new file mode 100644 index 0000000..7c69527 --- /dev/null +++ b/Qwen3-4B-tau2-grpo-v0.1.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bf96994c1c5ce205638a4ff5204a6ce1330aeaee0b89cd886cfda5d0096d1e5 +size 1814374272 diff --git a/Qwen3-4B-tau2-grpo-v0.1.i1-IQ3_XXS.gguf b/Qwen3-4B-tau2-grpo-v0.1.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..6a5641d --- /dev/null +++ b/Qwen3-4B-tau2-grpo-v0.1.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:895dc0316b906796c6e4f77c992a84fe63fb70ffd7d40572f986c8782c22f550 +size 1670187392 diff --git a/Qwen3-4B-tau2-grpo-v0.1.i1-IQ4_NL.gguf b/Qwen3-4B-tau2-grpo-v0.1.i1-IQ4_NL.gguf new file mode 100644 index 0000000..2fefa52 --- /dev/null +++ b/Qwen3-4B-tau2-grpo-v0.1.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c60bd68bcbf8e63566da5f2ba80b6d09706bf85160dd165a8d7a513d1671af9d +size 2381342592 diff --git a/Qwen3-4B-tau2-grpo-v0.1.i1-IQ4_XS.gguf b/Qwen3-4B-tau2-grpo-v0.1.i1-IQ4_XS.gguf new file mode 100644 index 0000000..78e3dec --- /dev/null +++ b/Qwen3-4B-tau2-grpo-v0.1.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:491ff755b55efa09602352270b063957aac8d118ad2a45518ca7973b3d4438a7 +size 2270750592 diff --git a/Qwen3-4B-tau2-grpo-v0.1.i1-Q2_K.gguf b/Qwen3-4B-tau2-grpo-v0.1.i1-Q2_K.gguf new file mode 100644 index 0000000..036a08a --- /dev/null +++ b/Qwen3-4B-tau2-grpo-v0.1.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74baadcfda28b393dc5e621ea9928779d98bc29db0c3f9dacc8306f31daa63f7 +size 1669498752 diff --git a/Qwen3-4B-tau2-grpo-v0.1.i1-Q2_K_S.gguf b/Qwen3-4B-tau2-grpo-v0.1.i1-Q2_K_S.gguf new file mode 100644 index 0000000..64cf7f0 --- /dev/null +++ b/Qwen3-4B-tau2-grpo-v0.1.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eedffa224d01312192ff70ce06b5fc4dff9d9d39c0f52e04b91fd8de79b30103 +size 1563453312 diff --git a/Qwen3-4B-tau2-grpo-v0.1.i1-Q3_K_L.gguf b/Qwen3-4B-tau2-grpo-v0.1.i1-Q3_K_L.gguf new file mode 100644 index 0000000..c2f2e48 --- /dev/null +++ b/Qwen3-4B-tau2-grpo-v0.1.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c831bbdf11d07e89d34de601b49a42f40c2cf8afded5164304491fac8e23a3da +size 2239784832 diff --git a/Qwen3-4B-tau2-grpo-v0.1.i1-Q3_K_M.gguf b/Qwen3-4B-tau2-grpo-v0.1.i1-Q3_K_M.gguf new file mode 100644 index 0000000..9eaa2eb --- /dev/null +++ b/Qwen3-4B-tau2-grpo-v0.1.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2175bf5488ad87f0cfe4e6c0c4ad36a927acc6e1a817bc31ee182a4cb0a50b53 +size 2075617152 diff --git a/Qwen3-4B-tau2-grpo-v0.1.i1-Q3_K_S.gguf b/Qwen3-4B-tau2-grpo-v0.1.i1-Q3_K_S.gguf new file mode 100644 index 0000000..2968b77 --- /dev/null +++ b/Qwen3-4B-tau2-grpo-v0.1.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f92b9f11961dd8ee1d29ed84342ea7f8e161d07e88e04d55e2dd14ca8bab1c0 +size 1886996352 diff --git a/Qwen3-4B-tau2-grpo-v0.1.i1-Q4_0.gguf b/Qwen3-4B-tau2-grpo-v0.1.i1-Q4_0.gguf new file mode 100644 index 0000000..d2f9f3d --- /dev/null +++ b/Qwen3-4B-tau2-grpo-v0.1.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c62f1b1cfa2c4040331d6719082cf458594e1cee1a7daed505144f696c791f3 +size 2375772032 diff --git a/Qwen3-4B-tau2-grpo-v0.1.i1-Q4_1.gguf b/Qwen3-4B-tau2-grpo-v0.1.i1-Q4_1.gguf new file mode 100644 index 0000000..a6a82b8 --- /dev/null +++ b/Qwen3-4B-tau2-grpo-v0.1.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cec6369d43ff4f9038ce88c0c179314663fbba988bef50e2ba1cc363d7d91e8 +size 2596628352 diff --git a/Qwen3-4B-tau2-grpo-v0.1.i1-Q4_K_M.gguf b/Qwen3-4B-tau2-grpo-v0.1.i1-Q4_K_M.gguf new file mode 100644 index 0000000..600271c --- /dev/null +++ b/Qwen3-4B-tau2-grpo-v0.1.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54e48fb17145dcb26e238a1ca003d39312008357649f4a9a5bce29b5e878a99f +size 2497279872 diff --git a/Qwen3-4B-tau2-grpo-v0.1.i1-Q4_K_S.gguf b/Qwen3-4B-tau2-grpo-v0.1.i1-Q4_K_S.gguf new file mode 100644 index 0000000..1e033cd --- /dev/null +++ b/Qwen3-4B-tau2-grpo-v0.1.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24592bd626f79e9b0bee76b2bec1267bca6812e69ce5c0f4ff7e91d64122bda9 +size 2383308672 diff --git a/Qwen3-4B-tau2-grpo-v0.1.i1-Q5_K_M.gguf b/Qwen3-4B-tau2-grpo-v0.1.i1-Q5_K_M.gguf new file mode 100644 index 0000000..8949bbc --- /dev/null +++ b/Qwen3-4B-tau2-grpo-v0.1.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4d0f1f2d37978ddaae5a335aa85900b3008da3658790fecf7beb76c2ce03df1 +size 2889512832 diff --git a/Qwen3-4B-tau2-grpo-v0.1.i1-Q5_K_S.gguf b/Qwen3-4B-tau2-grpo-v0.1.i1-Q5_K_S.gguf new file mode 100644 index 0000000..ad350b2 --- /dev/null +++ b/Qwen3-4B-tau2-grpo-v0.1.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8e7a3560ae0d23cc272a237a1d37c10af384bcb87b6e6e9464ae690a332ac89 +size 2823710592 diff --git a/Qwen3-4B-tau2-grpo-v0.1.i1-Q6_K.gguf b/Qwen3-4B-tau2-grpo-v0.1.i1-Q6_K.gguf new file mode 100644 index 0000000..6561df0 --- /dev/null +++ b/Qwen3-4B-tau2-grpo-v0.1.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7ac0d4cc452a74247ca39ff031c56639a910ee8ba0e3c5519530ecc5ddce758 +size 3306260352 diff --git a/Qwen3-4B-tau2-grpo-v0.1.imatrix.gguf b/Qwen3-4B-tau2-grpo-v0.1.imatrix.gguf new file mode 100644 index 0000000..259eed4 --- /dev/null +++ b/Qwen3-4B-tau2-grpo-v0.1.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b165e46d350e3279d250b82e5eae974a28635e5f9f55ab80b2bc5ea9fe82fe2 +size 3872640 diff --git a/README.md b/README.md new file mode 100644 index 0000000..be299b7 --- /dev/null +++ b/README.md @@ -0,0 +1,86 @@ +--- +base_model: zjxia/Qwen3-4B-tau2-grpo-v0.1 +language: +- en +library_name: transformers +license: apache-2.0 +license_link: https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507/blob/main/LICENSE +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/zjxia/Qwen3-4B-tau2-grpo-v0.1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-4B-tau2-grpo-v0.1-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Qwen3-4B-tau2-grpo-v0.1-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/Qwen3-4B-tau2-grpo-v0.1-i1-GGUF/resolve/main/Qwen3-4B-tau2-grpo-v0.1.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tau2-grpo-v0.1-i1-GGUF/resolve/main/Qwen3-4B-tau2-grpo-v0.1.i1-IQ1_S.gguf) | i1-IQ1_S | 1.2 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tau2-grpo-v0.1-i1-GGUF/resolve/main/Qwen3-4B-tau2-grpo-v0.1.i1-IQ1_M.gguf) | i1-IQ1_M | 1.2 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tau2-grpo-v0.1-i1-GGUF/resolve/main/Qwen3-4B-tau2-grpo-v0.1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tau2-grpo-v0.1-i1-GGUF/resolve/main/Qwen3-4B-tau2-grpo-v0.1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tau2-grpo-v0.1-i1-GGUF/resolve/main/Qwen3-4B-tau2-grpo-v0.1.i1-IQ2_S.gguf) | i1-IQ2_S | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tau2-grpo-v0.1-i1-GGUF/resolve/main/Qwen3-4B-tau2-grpo-v0.1.i1-IQ2_M.gguf) | i1-IQ2_M | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tau2-grpo-v0.1-i1-GGUF/resolve/main/Qwen3-4B-tau2-grpo-v0.1.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.7 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tau2-grpo-v0.1-i1-GGUF/resolve/main/Qwen3-4B-tau2-grpo-v0.1.i1-Q2_K.gguf) | i1-Q2_K | 1.8 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tau2-grpo-v0.1-i1-GGUF/resolve/main/Qwen3-4B-tau2-grpo-v0.1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tau2-grpo-v0.1-i1-GGUF/resolve/main/Qwen3-4B-tau2-grpo-v0.1.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tau2-grpo-v0.1-i1-GGUF/resolve/main/Qwen3-4B-tau2-grpo-v0.1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 2.0 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tau2-grpo-v0.1-i1-GGUF/resolve/main/Qwen3-4B-tau2-grpo-v0.1.i1-IQ3_S.gguf) | i1-IQ3_S | 2.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tau2-grpo-v0.1-i1-GGUF/resolve/main/Qwen3-4B-tau2-grpo-v0.1.i1-IQ3_M.gguf) | i1-IQ3_M | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tau2-grpo-v0.1-i1-GGUF/resolve/main/Qwen3-4B-tau2-grpo-v0.1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 2.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tau2-grpo-v0.1-i1-GGUF/resolve/main/Qwen3-4B-tau2-grpo-v0.1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 2.3 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tau2-grpo-v0.1-i1-GGUF/resolve/main/Qwen3-4B-tau2-grpo-v0.1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tau2-grpo-v0.1-i1-GGUF/resolve/main/Qwen3-4B-tau2-grpo-v0.1.i1-Q4_0.gguf) | i1-Q4_0 | 2.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tau2-grpo-v0.1-i1-GGUF/resolve/main/Qwen3-4B-tau2-grpo-v0.1.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tau2-grpo-v0.1-i1-GGUF/resolve/main/Qwen3-4B-tau2-grpo-v0.1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.5 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tau2-grpo-v0.1-i1-GGUF/resolve/main/Qwen3-4B-tau2-grpo-v0.1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tau2-grpo-v0.1-i1-GGUF/resolve/main/Qwen3-4B-tau2-grpo-v0.1.i1-Q4_1.gguf) | i1-Q4_1 | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tau2-grpo-v0.1-i1-GGUF/resolve/main/Qwen3-4B-tau2-grpo-v0.1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tau2-grpo-v0.1-i1-GGUF/resolve/main/Qwen3-4B-tau2-grpo-v0.1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tau2-grpo-v0.1-i1-GGUF/resolve/main/Qwen3-4B-tau2-grpo-v0.1.i1-Q6_K.gguf) | i1-Q6_K | 3.4 | 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. + +