commit ec337b4e233bf6926a9440340e9c0b6e9b54a4a9 Author: ModelHub XC Date: Tue Oct 6 03:03:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-1.5B-Matrix-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..617ebcf --- /dev/null +++ b/.gitattributes @@ -0,0 +1,58 @@ +*.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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Matrix.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Matrix.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Matrix.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Matrix.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Matrix.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Matrix.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Matrix.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Matrix.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Matrix.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Matrix.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Matrix.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Matrix.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Matrix.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Matrix.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Matrix.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Matrix.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Matrix.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Matrix.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Matrix.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Matrix.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Matrix.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Matrix.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-1.5B-Matrix.i1-IQ1_M.gguf b/Qwen2.5-1.5B-Matrix.i1-IQ1_M.gguf new file mode 100644 index 0000000..dd6f697 --- /dev/null +++ b/Qwen2.5-1.5B-Matrix.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1486ef202974f2630aabe749cc13b34d56aa58b25ed277731dc44296a24a1ed +size 541038464 diff --git a/Qwen2.5-1.5B-Matrix.i1-IQ1_S.gguf b/Qwen2.5-1.5B-Matrix.i1-IQ1_S.gguf new file mode 100644 index 0000000..ff1ebba --- /dev/null +++ b/Qwen2.5-1.5B-Matrix.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f13452585c3e8c489e1d45bac29d06af0f2e91ac5f90ad8e32e3ad996fecebb +size 513104768 diff --git a/Qwen2.5-1.5B-Matrix.i1-IQ2_M.gguf b/Qwen2.5-1.5B-Matrix.i1-IQ2_M.gguf new file mode 100644 index 0000000..4207609 --- /dev/null +++ b/Qwen2.5-1.5B-Matrix.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbcb5b8ccc33a61d98130ec0a008e46a9ea02bf2c8d6011e916750921ecd502b +size 701333888 diff --git a/Qwen2.5-1.5B-Matrix.i1-IQ2_S.gguf b/Qwen2.5-1.5B-Matrix.i1-IQ2_S.gguf new file mode 100644 index 0000000..08f7685 --- /dev/null +++ b/Qwen2.5-1.5B-Matrix.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:557369c357698b3d314a86b2c99bd3765b6e02ef11bcd1e7401b615a017f6bb1 +size 664088960 diff --git a/Qwen2.5-1.5B-Matrix.i1-IQ2_XS.gguf b/Qwen2.5-1.5B-Matrix.i1-IQ2_XS.gguf new file mode 100644 index 0000000..ae914f0 --- /dev/null +++ b/Qwen2.5-1.5B-Matrix.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:589117fbccea8431d16572a4ff747cee4bb91eb479d62cf93eef1598e7a30c4e +size 626903936 diff --git a/Qwen2.5-1.5B-Matrix.i1-IQ2_XXS.gguf b/Qwen2.5-1.5B-Matrix.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..865272a --- /dev/null +++ b/Qwen2.5-1.5B-Matrix.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78fd55830dddfd6806529588aefdb3204ee9139aa37eb422a1aa989e0ebcbad2 +size 587594624 diff --git a/Qwen2.5-1.5B-Matrix.i1-IQ3_M.gguf b/Qwen2.5-1.5B-Matrix.i1-IQ3_M.gguf new file mode 100644 index 0000000..3ea8823 --- /dev/null +++ b/Qwen2.5-1.5B-Matrix.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12bde73e5cfbd83df820f86b35c06c20608adfd2f3e8966686e1c12a796ee156 +size 876943232 diff --git a/Qwen2.5-1.5B-Matrix.i1-IQ3_S.gguf b/Qwen2.5-1.5B-Matrix.i1-IQ3_S.gguf new file mode 100644 index 0000000..c48a913 --- /dev/null +++ b/Qwen2.5-1.5B-Matrix.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccaaf18f081edd2103fe878108c0fc88490d498d1d7748943e816658f887cda5 +size 862686080 diff --git a/Qwen2.5-1.5B-Matrix.i1-IQ3_XS.gguf b/Qwen2.5-1.5B-Matrix.i1-IQ3_XS.gguf new file mode 100644 index 0000000..051972a --- /dev/null +++ b/Qwen2.5-1.5B-Matrix.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f181de9bd08ead4e7b48b82fe1140618ecc10dc685bff993edd17c35efda30ba +size 831978368 diff --git a/Qwen2.5-1.5B-Matrix.i1-IQ3_XXS.gguf b/Qwen2.5-1.5B-Matrix.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..ff85eb0 --- /dev/null +++ b/Qwen2.5-1.5B-Matrix.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7907a87c8c225fbdc162d1d2b5e0f87ff500ca7f17aaf43e28c5ed9e675089ea +size 769071488 diff --git a/Qwen2.5-1.5B-Matrix.i1-IQ4_XS.gguf b/Qwen2.5-1.5B-Matrix.i1-IQ4_XS.gguf new file mode 100644 index 0000000..f0e4019 --- /dev/null +++ b/Qwen2.5-1.5B-Matrix.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:438d74413d33b73ed832c2490831064c0033dcc7a913f4352b853fd2fdbf2bac +size 1019712896 diff --git a/Qwen2.5-1.5B-Matrix.i1-Q2_K.gguf b/Qwen2.5-1.5B-Matrix.i1-Q2_K.gguf new file mode 100644 index 0000000..266b042 --- /dev/null +++ b/Qwen2.5-1.5B-Matrix.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ffaf0f7ef57b94fe09f077e845c50e16df3e0fbd8eea355b5d7f6cce1323bf9 +size 752882048 diff --git a/Qwen2.5-1.5B-Matrix.i1-Q3_K_L.gguf b/Qwen2.5-1.5B-Matrix.i1-Q3_K_L.gguf new file mode 100644 index 0000000..975d5df --- /dev/null +++ b/Qwen2.5-1.5B-Matrix.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:881d728c806abf0b558cf40c76e69f0c56e88ecd12956e837537f6ead55d6873 +size 980441984 diff --git a/Qwen2.5-1.5B-Matrix.i1-Q3_K_M.gguf b/Qwen2.5-1.5B-Matrix.i1-Q3_K_M.gguf new file mode 100644 index 0000000..4e4caec --- /dev/null +++ b/Qwen2.5-1.5B-Matrix.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eef1f32ef45752cafd329f56b1aca62a2f347b083d8a36df7f1da15e4d4dfa52 +size 924457856 diff --git a/Qwen2.5-1.5B-Matrix.i1-Q3_K_S.gguf b/Qwen2.5-1.5B-Matrix.i1-Q3_K_S.gguf new file mode 100644 index 0000000..30c0c42 --- /dev/null +++ b/Qwen2.5-1.5B-Matrix.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:198ec452b19956b9bf2004a7133abd400522473ff32e0da61e1d2f0450d4f5be +size 861223808 diff --git a/Qwen2.5-1.5B-Matrix.i1-Q4_0.gguf b/Qwen2.5-1.5B-Matrix.i1-Q4_0.gguf new file mode 100644 index 0000000..0cca6bd --- /dev/null +++ b/Qwen2.5-1.5B-Matrix.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6d83d18735f420ca51f82e788472c78d7fe6edb948bb255223ec967beacb569 +size 1068809600 diff --git a/Qwen2.5-1.5B-Matrix.i1-Q4_0_4_4.gguf b/Qwen2.5-1.5B-Matrix.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..0bbb34d --- /dev/null +++ b/Qwen2.5-1.5B-Matrix.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33646022ef476e8ff6005644e70ba065e2fb527b487639f269cdda6a1bf79a87 +size 1066229120 diff --git a/Qwen2.5-1.5B-Matrix.i1-Q4_0_4_8.gguf b/Qwen2.5-1.5B-Matrix.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..025bfbd --- /dev/null +++ b/Qwen2.5-1.5B-Matrix.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ed5348c9b1ca618d639d1163c017708f9f145924263ac01e99d6b8c5e465c7c +size 1066229120 diff --git a/Qwen2.5-1.5B-Matrix.i1-Q4_0_8_8.gguf b/Qwen2.5-1.5B-Matrix.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..b468659 --- /dev/null +++ b/Qwen2.5-1.5B-Matrix.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6675cdac5374c050ec79513bfefd5b01694ab2927b8ea5675f8ec8a71dd37d04 +size 1066229120 diff --git a/Qwen2.5-1.5B-Matrix.i1-Q4_K_M.gguf b/Qwen2.5-1.5B-Matrix.i1-Q4_K_M.gguf new file mode 100644 index 0000000..e37aa04 --- /dev/null +++ b/Qwen2.5-1.5B-Matrix.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c24066acebe97aa7563e65381086236ecdf4348547e973217f0443e6d2b7e9f8 +size 1117322624 diff --git a/Qwen2.5-1.5B-Matrix.i1-Q4_K_S.gguf b/Qwen2.5-1.5B-Matrix.i1-Q4_K_S.gguf new file mode 100644 index 0000000..7c113d5 --- /dev/null +++ b/Qwen2.5-1.5B-Matrix.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ce49a91f05315a9ef26a95ea3379629ddaca6976cfa23d360a02b67e79abc4f +size 1071586688 diff --git a/Qwen2.5-1.5B-Matrix.i1-Q5_K_M.gguf b/Qwen2.5-1.5B-Matrix.i1-Q5_K_M.gguf new file mode 100644 index 0000000..531814b --- /dev/null +++ b/Qwen2.5-1.5B-Matrix.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2287aeb9deaf722f1164df67b2e8bf94bbccb8bfeab5edf111e5946ca1658098 +size 1285496192 diff --git a/Qwen2.5-1.5B-Matrix.i1-Q5_K_S.gguf b/Qwen2.5-1.5B-Matrix.i1-Q5_K_S.gguf new file mode 100644 index 0000000..94f9017 --- /dev/null +++ b/Qwen2.5-1.5B-Matrix.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e90899732f9c0578ac6cd84c4c67e28c8e1d2bbcb5d13ba7709366476170084 +size 1259175296 diff --git a/Qwen2.5-1.5B-Matrix.i1-Q6_K.gguf b/Qwen2.5-1.5B-Matrix.i1-Q6_K.gguf new file mode 100644 index 0000000..3312203 --- /dev/null +++ b/Qwen2.5-1.5B-Matrix.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edf82635f1bb6e0b9f573d57127351fe56a6ae7c109d89f7d0d53072f71b4f02 +size 1464180608 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a3e25b8 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: bunnycore/Qwen2.5-1.5B-Matrix +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/bunnycore/Qwen2.5-1.5B-Matrix + + +static quants are available at https://huggingface.co/mradermacher/Qwen2.5-1.5B-Matrix-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/Qwen2.5-1.5B-Matrix-i1-GGUF/resolve/main/Qwen2.5-1.5B-Matrix.i1-IQ1_S.gguf) | i1-IQ1_S | 0.6 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Matrix-i1-GGUF/resolve/main/Qwen2.5-1.5B-Matrix.i1-IQ1_M.gguf) | i1-IQ1_M | 0.6 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Matrix-i1-GGUF/resolve/main/Qwen2.5-1.5B-Matrix.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Matrix-i1-GGUF/resolve/main/Qwen2.5-1.5B-Matrix.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Matrix-i1-GGUF/resolve/main/Qwen2.5-1.5B-Matrix.i1-IQ2_S.gguf) | i1-IQ2_S | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Matrix-i1-GGUF/resolve/main/Qwen2.5-1.5B-Matrix.i1-IQ2_M.gguf) | i1-IQ2_M | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Matrix-i1-GGUF/resolve/main/Qwen2.5-1.5B-Matrix.i1-Q2_K.gguf) | i1-Q2_K | 0.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Matrix-i1-GGUF/resolve/main/Qwen2.5-1.5B-Matrix.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Matrix-i1-GGUF/resolve/main/Qwen2.5-1.5B-Matrix.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Matrix-i1-GGUF/resolve/main/Qwen2.5-1.5B-Matrix.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.0 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Matrix-i1-GGUF/resolve/main/Qwen2.5-1.5B-Matrix.i1-IQ3_S.gguf) | i1-IQ3_S | 1.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Matrix-i1-GGUF/resolve/main/Qwen2.5-1.5B-Matrix.i1-IQ3_M.gguf) | i1-IQ3_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Matrix-i1-GGUF/resolve/main/Qwen2.5-1.5B-Matrix.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.0 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Matrix-i1-GGUF/resolve/main/Qwen2.5-1.5B-Matrix.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.1 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Matrix-i1-GGUF/resolve/main/Qwen2.5-1.5B-Matrix.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Matrix-i1-GGUF/resolve/main/Qwen2.5-1.5B-Matrix.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 1.2 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Matrix-i1-GGUF/resolve/main/Qwen2.5-1.5B-Matrix.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 1.2 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Matrix-i1-GGUF/resolve/main/Qwen2.5-1.5B-Matrix.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 1.2 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Matrix-i1-GGUF/resolve/main/Qwen2.5-1.5B-Matrix.i1-Q4_0.gguf) | i1-Q4_0 | 1.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Matrix-i1-GGUF/resolve/main/Qwen2.5-1.5B-Matrix.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.2 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Matrix-i1-GGUF/resolve/main/Qwen2.5-1.5B-Matrix.i1-Q4_K_M.gguf) | i1-Q4_K_M | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Matrix-i1-GGUF/resolve/main/Qwen2.5-1.5B-Matrix.i1-Q5_K_S.gguf) | i1-Q5_K_S | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Matrix-i1-GGUF/resolve/main/Qwen2.5-1.5B-Matrix.i1-Q5_K_M.gguf) | i1-Q5_K_M | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Matrix-i1-GGUF/resolve/main/Qwen2.5-1.5B-Matrix.i1-Q6_K.gguf) | i1-Q6_K | 1.6 | 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..8b0c888 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1269b5439b204f41791756d58acda95593c1675c8d6106c24abb062585cfac3 +size 2042201