commit 6a592fbadb2bb4f9424a977ef8f886cc4eaa119e Author: ModelHub XC Date: Thu Apr 30 18:23:08 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-0.5b-RBase-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..43bc2c0 --- /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 +Qwen2.5-0.5b-RBase.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5b-RBase.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5b-RBase.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5b-RBase.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5b-RBase.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5b-RBase.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5b-RBase.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5b-RBase.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5b-RBase.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5b-RBase.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5b-RBase.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5b-RBase.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5b-RBase.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5b-RBase.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5b-RBase.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5b-RBase.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5b-RBase.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5b-RBase.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5b-RBase.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5b-RBase.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5b-RBase.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5b-RBase.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5b-RBase.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5b-RBase.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-0.5b-RBase.i1-IQ1_M.gguf b/Qwen2.5-0.5b-RBase.i1-IQ1_M.gguf new file mode 100644 index 0000000..4643a9d --- /dev/null +++ b/Qwen2.5-0.5b-RBase.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac7c255952f5d01402c87aae4a47977db79105583624805e27227981d3019666 +size 317972896 diff --git a/Qwen2.5-0.5b-RBase.i1-IQ1_S.gguf b/Qwen2.5-0.5b-RBase.i1-IQ1_S.gguf new file mode 100644 index 0000000..b961388 --- /dev/null +++ b/Qwen2.5-0.5b-RBase.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecce4a102ea82e9486eab557fd936c3e0c8bc64643b1a764ba0365eeaf065d33 +size 315827872 diff --git a/Qwen2.5-0.5b-RBase.i1-IQ2_M.gguf b/Qwen2.5-0.5b-RBase.i1-IQ2_M.gguf new file mode 100644 index 0000000..33d9f3d --- /dev/null +++ b/Qwen2.5-0.5b-RBase.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0828d896180585ea8f8d06831898e3e726eb44a327491a21990249c407dcb4f6 +size 328595872 diff --git a/Qwen2.5-0.5b-RBase.i1-IQ2_S.gguf b/Qwen2.5-0.5b-RBase.i1-IQ2_S.gguf new file mode 100644 index 0000000..db2b8ee --- /dev/null +++ b/Qwen2.5-0.5b-RBase.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8ea3dd2f0d423a5933303a222bca515ae855368cab39f60b0fea6e2573d0d19 +size 325735840 diff --git a/Qwen2.5-0.5b-RBase.i1-IQ2_XS.gguf b/Qwen2.5-0.5b-RBase.i1-IQ2_XS.gguf new file mode 100644 index 0000000..da082f5 --- /dev/null +++ b/Qwen2.5-0.5b-RBase.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5363c6234556c945ed180de536973399c4fd1ba7506780660e5318d0531717a +size 324407968 diff --git a/Qwen2.5-0.5b-RBase.i1-IQ2_XXS.gguf b/Qwen2.5-0.5b-RBase.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..34ae420 --- /dev/null +++ b/Qwen2.5-0.5b-RBase.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afb4a6ccd28fd3e8fb23294e1c1acb4ebbb672baedf802b4c3443bf54275b84a +size 321547936 diff --git a/Qwen2.5-0.5b-RBase.i1-IQ3_M.gguf b/Qwen2.5-0.5b-RBase.i1-IQ3_M.gguf new file mode 100644 index 0000000..e673124 --- /dev/null +++ b/Qwen2.5-0.5b-RBase.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76fb3973a43483650b497f6c1b64ae570ff764f35422ef9850a34812fdff0135 +size 342750880 diff --git a/Qwen2.5-0.5b-RBase.i1-IQ3_S.gguf b/Qwen2.5-0.5b-RBase.i1-IQ3_S.gguf new file mode 100644 index 0000000..533704a --- /dev/null +++ b/Qwen2.5-0.5b-RBase.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:975e0b8ef528d9a026a6bf37ed68a8d4a8942390a27b03f9aedf6a6d5f1c7284 +size 338605984 diff --git a/Qwen2.5-0.5b-RBase.i1-IQ3_XS.gguf b/Qwen2.5-0.5b-RBase.i1-IQ3_XS.gguf new file mode 100644 index 0000000..09a637a --- /dev/null +++ b/Qwen2.5-0.5b-RBase.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:249982b9c6a3c11df0b85d8666606e9683e23b53f5061a61cdef31fcbbbc3045 +size 338605984 diff --git a/Qwen2.5-0.5b-RBase.i1-IQ3_XXS.gguf b/Qwen2.5-0.5b-RBase.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..6c95516 --- /dev/null +++ b/Qwen2.5-0.5b-RBase.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8af4d7ea9a0b4a2162b543971c7992afd83ad7e7165aa8ee4f122c3620019124 +size 333703072 diff --git a/Qwen2.5-0.5b-RBase.i1-IQ4_XS.gguf b/Qwen2.5-0.5b-RBase.i1-IQ4_XS.gguf new file mode 100644 index 0000000..2f77ff7 --- /dev/null +++ b/Qwen2.5-0.5b-RBase.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cfe7442650e70982f15f3d7c4eabb3f16a6a1170e5edc824904b54b6ad5c272 +size 349400992 diff --git a/Qwen2.5-0.5b-RBase.i1-Q2_K.gguf b/Qwen2.5-0.5b-RBase.i1-Q2_K.gguf new file mode 100644 index 0000000..bdb6769 --- /dev/null +++ b/Qwen2.5-0.5b-RBase.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:980f23e657c4db245c426ff34471a586998395ddbe6e093e0bb525754356d304 +size 338605984 diff --git a/Qwen2.5-0.5b-RBase.i1-Q3_K_L.gguf b/Qwen2.5-0.5b-RBase.i1-Q3_K_L.gguf new file mode 100644 index 0000000..a9efce5 --- /dev/null +++ b/Qwen2.5-0.5b-RBase.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbf1f68d8eff25deb4a0ad3c3ab86c1e82cc395ee87925f767b7970c5d8427a9 +size 369356704 diff --git a/Qwen2.5-0.5b-RBase.i1-Q3_K_M.gguf b/Qwen2.5-0.5b-RBase.i1-Q3_K_M.gguf new file mode 100644 index 0000000..0abc823 --- /dev/null +++ b/Qwen2.5-0.5b-RBase.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90e457fb0e47886e9a03d20e4d2795e97740248c479d7742d4d818894e2912f1 +size 355465120 diff --git a/Qwen2.5-0.5b-RBase.i1-Q3_K_S.gguf b/Qwen2.5-0.5b-RBase.i1-Q3_K_S.gguf new file mode 100644 index 0000000..2fd8b40 --- /dev/null +++ b/Qwen2.5-0.5b-RBase.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae81dbbc383fecea1227f73e0f7e9a30d0ff2b03ebec7db9b5fb49b02cb7ffa3 +size 338261920 diff --git a/Qwen2.5-0.5b-RBase.i1-Q4_0.gguf b/Qwen2.5-0.5b-RBase.i1-Q4_0.gguf new file mode 100644 index 0000000..c678e2a --- /dev/null +++ b/Qwen2.5-0.5b-RBase.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bbb32c6fba350f5c322cfdc3737302c65fd7c6b29b730f5fe83a11b668fb2c7 +size 352970656 diff --git a/Qwen2.5-0.5b-RBase.i1-Q4_0_4_4.gguf b/Qwen2.5-0.5b-RBase.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..1fce315 --- /dev/null +++ b/Qwen2.5-0.5b-RBase.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20bd77aa358994a701f35678f8e599fecdc504e258e038130621f7f55d3135ae +size 352153504 diff --git a/Qwen2.5-0.5b-RBase.i1-Q4_0_4_8.gguf b/Qwen2.5-0.5b-RBase.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..72d7976 --- /dev/null +++ b/Qwen2.5-0.5b-RBase.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21e95adb3bbef2a63596e1a7ad7b239385e796d0bd0bbb6f4d6654133271bca3 +size 352153504 diff --git a/Qwen2.5-0.5b-RBase.i1-Q4_0_8_8.gguf b/Qwen2.5-0.5b-RBase.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..f44dd12 --- /dev/null +++ b/Qwen2.5-0.5b-RBase.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f39a0331eb918aaf44d9fcfd953fe5d87fa632cad8752c357c061527133b4ff0 +size 352153504 diff --git a/Qwen2.5-0.5b-RBase.i1-Q4_K_M.gguf b/Qwen2.5-0.5b-RBase.i1-Q4_K_M.gguf new file mode 100644 index 0000000..25f6b18 --- /dev/null +++ b/Qwen2.5-0.5b-RBase.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8db1c9f20f11ad96152a05e5713500efc32cc9497b6ca6b80f0f2cfd052cfec6 +size 397806496 diff --git a/Qwen2.5-0.5b-RBase.i1-Q4_K_S.gguf b/Qwen2.5-0.5b-RBase.i1-Q4_K_S.gguf new file mode 100644 index 0000000..a57fda7 --- /dev/null +++ b/Qwen2.5-0.5b-RBase.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5059adab58c17a1a9c56beb729ab66961bb9c24240ad8d6743706f4a5c2c0eaa +size 385470368 diff --git a/Qwen2.5-0.5b-RBase.i1-Q5_K_M.gguf b/Qwen2.5-0.5b-RBase.i1-Q5_K_M.gguf new file mode 100644 index 0000000..28d941c --- /dev/null +++ b/Qwen2.5-0.5b-RBase.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:690fe14655c2f1ae416bc91fa0cbc9483f243b47d0ec432d11ee1f7e7b156f4a +size 420084640 diff --git a/Qwen2.5-0.5b-RBase.i1-Q5_K_S.gguf b/Qwen2.5-0.5b-RBase.i1-Q5_K_S.gguf new file mode 100644 index 0000000..8efc966 --- /dev/null +++ b/Qwen2.5-0.5b-RBase.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e08d51d670020bbc6983b11db2bf8d21dd128270017b0fd540ea82a2739c3539 +size 412708768 diff --git a/Qwen2.5-0.5b-RBase.i1-Q6_K.gguf b/Qwen2.5-0.5b-RBase.i1-Q6_K.gguf new file mode 100644 index 0000000..17f8612 --- /dev/null +++ b/Qwen2.5-0.5b-RBase.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85bce146e69355f0f7ce5abfc71ad0d679838f469ad3d6690a2a95bc5cdea827 +size 505735072 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c14f713 --- /dev/null +++ b/README.md @@ -0,0 +1,95 @@ +--- +base_model: KingNish/Qwen2.5-0.5b-RBase +language: +- zho +- eng +- fra +- spa +- por +- deu +- ita +- rus +- jpn +- kor +- vie +- tha +- ara +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen2 +- trl +- sft +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/KingNish/Qwen2.5-0.5b-RBase + + +static quants are available at https://huggingface.co/mradermacher/Qwen2.5-0.5b-RBase-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/Qwen2.5-0.5b-RBase-i1-GGUF/resolve/main/Qwen2.5-0.5b-RBase.i1-IQ1_S.gguf) | i1-IQ1_S | 0.4 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5b-RBase-i1-GGUF/resolve/main/Qwen2.5-0.5b-RBase.i1-IQ1_M.gguf) | i1-IQ1_M | 0.4 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5b-RBase-i1-GGUF/resolve/main/Qwen2.5-0.5b-RBase.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5b-RBase-i1-GGUF/resolve/main/Qwen2.5-0.5b-RBase.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5b-RBase-i1-GGUF/resolve/main/Qwen2.5-0.5b-RBase.i1-IQ2_S.gguf) | i1-IQ2_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5b-RBase-i1-GGUF/resolve/main/Qwen2.5-0.5b-RBase.i1-IQ2_M.gguf) | i1-IQ2_M | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5b-RBase-i1-GGUF/resolve/main/Qwen2.5-0.5b-RBase.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5b-RBase-i1-GGUF/resolve/main/Qwen2.5-0.5b-RBase.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.4 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5b-RBase-i1-GGUF/resolve/main/Qwen2.5-0.5b-RBase.i1-IQ3_S.gguf) | i1-IQ3_S | 0.4 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5b-RBase-i1-GGUF/resolve/main/Qwen2.5-0.5b-RBase.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5b-RBase-i1-GGUF/resolve/main/Qwen2.5-0.5b-RBase.i1-Q2_K.gguf) | i1-Q2_K | 0.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5b-RBase-i1-GGUF/resolve/main/Qwen2.5-0.5b-RBase.i1-IQ3_M.gguf) | i1-IQ3_M | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5b-RBase-i1-GGUF/resolve/main/Qwen2.5-0.5b-RBase.i1-IQ4_XS.gguf) | i1-IQ4_XS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5b-RBase-i1-GGUF/resolve/main/Qwen2.5-0.5b-RBase.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 0.5 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5b-RBase-i1-GGUF/resolve/main/Qwen2.5-0.5b-RBase.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 0.5 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5b-RBase-i1-GGUF/resolve/main/Qwen2.5-0.5b-RBase.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 0.5 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5b-RBase-i1-GGUF/resolve/main/Qwen2.5-0.5b-RBase.i1-Q4_0.gguf) | i1-Q4_0 | 0.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5b-RBase-i1-GGUF/resolve/main/Qwen2.5-0.5b-RBase.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.5 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5b-RBase-i1-GGUF/resolve/main/Qwen2.5-0.5b-RBase.i1-Q3_K_L.gguf) | i1-Q3_K_L | 0.5 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5b-RBase-i1-GGUF/resolve/main/Qwen2.5-0.5b-RBase.i1-Q4_K_S.gguf) | i1-Q4_K_S | 0.5 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5b-RBase-i1-GGUF/resolve/main/Qwen2.5-0.5b-RBase.i1-Q4_K_M.gguf) | i1-Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5b-RBase-i1-GGUF/resolve/main/Qwen2.5-0.5b-RBase.i1-Q5_K_S.gguf) | i1-Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5b-RBase-i1-GGUF/resolve/main/Qwen2.5-0.5b-RBase.i1-Q5_K_M.gguf) | i1-Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5b-RBase-i1-GGUF/resolve/main/Qwen2.5-0.5b-RBase.i1-Q6_K.gguf) | i1-Q6_K | 0.6 | 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. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..2b84b17 Binary files /dev/null and b/imatrix.dat differ