commit 53f1eab4857ac49ec9de28c1f325d1bd4c532ce8 Author: ModelHub XC Date: Thu Jun 4 02:32:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8c43083 --- /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-Instruct-2507-heretic-v3-quantized-processing.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ1_M.gguf b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ1_M.gguf new file mode 100644 index 0000000..73024fc --- /dev/null +++ b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f944742129bf45d65f7cde64550452adbaa390688a5c1c34c3a3dee803ae334 +size 1127017088 diff --git a/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ1_S.gguf b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ1_S.gguf new file mode 100644 index 0000000..0c64367 --- /dev/null +++ b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0185d6eb9994b14a59980c5d935ffb6d9051cb1efe433d292b0e9b87c816291a +size 1055255168 diff --git a/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ2_M.gguf b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ2_M.gguf new file mode 100644 index 0000000..492866c --- /dev/null +++ b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e2a689681fbc2dc3dd4afdad585a6938ddd23069ee7ee41b61a907110295a2b +size 1512983168 diff --git a/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ2_S.gguf b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ2_S.gguf new file mode 100644 index 0000000..1dad6c3 --- /dev/null +++ b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ad8a1ef3d2591fa6f00f342dea345d8faacf1157be5f29fd58a92d91cd6e1cb +size 1417300608 diff --git a/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ2_XS.gguf b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ2_XS.gguf new file mode 100644 index 0000000..baac949 --- /dev/null +++ b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bf1a45b577f3f77cb3ee97e5b24dd8c6a31f9d491b6d685a1ef1537d6613acc +size 1354099328 diff --git a/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ2_XXS.gguf b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..0093d40 --- /dev/null +++ b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ad24773c086c7915648ae16b55871960f58d4282ed9317a18f16e0b47e654bd +size 1246620288 diff --git a/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ3_M.gguf b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ3_M.gguf new file mode 100644 index 0000000..13c9e0e --- /dev/null +++ b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0e9ff7446318293f3186bb023fb620eb2f5fbb98080f45b8d16183803f99df7 +size 1962895488 diff --git a/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ3_S.gguf b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ3_S.gguf new file mode 100644 index 0000000..a96003f --- /dev/null +++ b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55ec1d8aa9dab085e868d0915cf99eabe954898feb1ccdbd7e8e77ac7f50017c +size 1899530368 diff --git a/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ3_XS.gguf b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ3_XS.gguf new file mode 100644 index 0000000..b53fc4c --- /dev/null +++ b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1806feddacd5f60ef773e285fa4d8757141c4179d29d7c44d56f5b82422ff0b +size 1814374528 diff --git a/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ3_XXS.gguf b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..4816915 --- /dev/null +++ b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da1ab61c1976986b7246d25931fc82fac88a4385a53025070de2ee59452d872e +size 1670187648 diff --git a/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ4_NL.gguf b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ4_NL.gguf new file mode 100644 index 0000000..e160030 --- /dev/null +++ b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34f8b03faa3dce6cfa5b3544a0e9475689e10be8b00d38695fa7b0bb72199da5 +size 2381342848 diff --git a/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ4_XS.gguf b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ4_XS.gguf new file mode 100644 index 0000000..a7a2d41 --- /dev/null +++ b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:297d8815d2a4a490d6688c29c8ba453af4c72d72a14f4a8415b8bc37b0098233 +size 2270750848 diff --git a/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q2_K.gguf b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q2_K.gguf new file mode 100644 index 0000000..454539a --- /dev/null +++ b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c94787b65080f259a39aa142cb0b436ec4830915a0fe03b88ee504b75b64505b +size 1669499008 diff --git a/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q2_K_S.gguf b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q2_K_S.gguf new file mode 100644 index 0000000..14c05ba --- /dev/null +++ b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2c6181940472d484a60add0baf2d6a68076c693c57b7beeb83f6a6708e6c5ad +size 1563453568 diff --git a/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q3_K_L.gguf b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q3_K_L.gguf new file mode 100644 index 0000000..47a9a79 --- /dev/null +++ b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c01c35ced976b5b3b57569425b16c1ed68313d358db979078565234c516953bb +size 2239785088 diff --git a/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q3_K_M.gguf b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q3_K_M.gguf new file mode 100644 index 0000000..66db804 --- /dev/null +++ b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27b96f006358928202ec49f5a83c2f7d3019ea732ea0b5ec5bb02f1f94d76572 +size 2075617408 diff --git a/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q3_K_S.gguf b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q3_K_S.gguf new file mode 100644 index 0000000..d975153 --- /dev/null +++ b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0bf63c1d310056eaba70dd3b66e8d90b04dc614e9898fe7e716975c127425dd +size 1886996608 diff --git a/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q4_0.gguf b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q4_0.gguf new file mode 100644 index 0000000..1e6d2c9 --- /dev/null +++ b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1724c8ff59b359aec49a3e37da68eb36c87ff1edb5e662a34f1d54f7ce4620f4 +size 2375772288 diff --git a/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q4_1.gguf b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q4_1.gguf new file mode 100644 index 0000000..305c646 --- /dev/null +++ b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5248a1e7b5fa137d9139a430b3278ab8f08eb9cf3212d6edccd27c8a65337e5a +size 2596628608 diff --git a/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q4_K_M.gguf b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q4_K_M.gguf new file mode 100644 index 0000000..4f57085 --- /dev/null +++ b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e6cded8a01cf02be0dedd5c1d67ab7a790c69fabdf0ee7709751cce2b896d18 +size 2497280128 diff --git a/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q4_K_S.gguf b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q4_K_S.gguf new file mode 100644 index 0000000..d3105c2 --- /dev/null +++ b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0389518e3509571bea2e6cc6b80c056d5251f6d593390e548ed941c841353001 +size 2383308928 diff --git a/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q5_K_M.gguf b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q5_K_M.gguf new file mode 100644 index 0000000..9d7f6ca --- /dev/null +++ b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8430568e63e594f36096647eea6295c34acd5da5633c6ff573edfa26787e5771 +size 2889513088 diff --git a/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q5_K_S.gguf b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q5_K_S.gguf new file mode 100644 index 0000000..f3d414f --- /dev/null +++ b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dc479b2f1c38863d3eb2d4378ede9a157f48f58ce447a70f4efa1dc19014650 +size 2823710848 diff --git a/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q6_K.gguf b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q6_K.gguf new file mode 100644 index 0000000..6518758 --- /dev/null +++ b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c6422b14d6544a2075ced8951b6e1f69160348e5b75a99ce9f3c1474257e695 +size 3306260608 diff --git a/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.imatrix.gguf b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.imatrix.gguf new file mode 100644 index 0000000..d4e9f83 --- /dev/null +++ b/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a52ee0461fef2da2dde52830d95d7d927afa61870ae1a8624a763d046116ab01 +size 3872640 diff --git a/README.md b/README.md new file mode 100644 index 0000000..199383a --- /dev/null +++ b/README.md @@ -0,0 +1,91 @@ +--- +base_model: p-e-w/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing +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 +tags: +- heretic +- uncensored +- decensored +- abliterated +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/p-e-w/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing-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-Instruct-2507-heretic-v3-quantized-processing-i1-GGUF/resolve/main/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing-i1-GGUF/resolve/main/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ1_S.gguf) | i1-IQ1_S | 1.2 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing-i1-GGUF/resolve/main/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ1_M.gguf) | i1-IQ1_M | 1.2 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing-i1-GGUF/resolve/main/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing-i1-GGUF/resolve/main/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing-i1-GGUF/resolve/main/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ2_S.gguf) | i1-IQ2_S | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing-i1-GGUF/resolve/main/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ2_M.gguf) | i1-IQ2_M | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing-i1-GGUF/resolve/main/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.7 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing-i1-GGUF/resolve/main/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q2_K.gguf) | i1-Q2_K | 1.8 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing-i1-GGUF/resolve/main/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing-i1-GGUF/resolve/main/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing-i1-GGUF/resolve/main/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q3_K_S.gguf) | i1-Q3_K_S | 2.0 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing-i1-GGUF/resolve/main/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ3_S.gguf) | i1-IQ3_S | 2.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing-i1-GGUF/resolve/main/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ3_M.gguf) | i1-IQ3_M | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing-i1-GGUF/resolve/main/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q3_K_M.gguf) | i1-Q3_K_M | 2.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing-i1-GGUF/resolve/main/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q3_K_L.gguf) | i1-Q3_K_L | 2.3 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing-i1-GGUF/resolve/main/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ4_XS.gguf) | i1-IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing-i1-GGUF/resolve/main/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q4_0.gguf) | i1-Q4_0 | 2.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing-i1-GGUF/resolve/main/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing-i1-GGUF/resolve/main/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.5 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing-i1-GGUF/resolve/main/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing-i1-GGUF/resolve/main/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q4_1.gguf) | i1-Q4_1 | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing-i1-GGUF/resolve/main/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing-i1-GGUF/resolve/main/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.i1-Q5_K_M.gguf) | i1-Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing-i1-GGUF/resolve/main/Qwen3-4B-Instruct-2507-heretic-v3-quantized-processing.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. + +