commit 625430cf6c4a3e951b3ca73b4c1cd072bf4feb97 Author: ModelHub XC Date: Tue Jul 14 13:54:06 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..53d7257 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 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 +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack 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 +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* 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 +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/Qwen_Qwen3-4B-Instruct-2507-IQ2_M.gguf b/Qwen_Qwen3-4B-Instruct-2507-IQ2_M.gguf new file mode 100644 index 0000000..4ff4f00 --- /dev/null +++ b/Qwen_Qwen3-4B-Instruct-2507-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b576b3c5483dd8a87eca98d84f83c653a755ccb48ab31b6567a69e207ee233b +size 1512983776 diff --git a/Qwen_Qwen3-4B-Instruct-2507-IQ3_M.gguf b/Qwen_Qwen3-4B-Instruct-2507-IQ3_M.gguf new file mode 100644 index 0000000..8cb21a4 --- /dev/null +++ b/Qwen_Qwen3-4B-Instruct-2507-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b458203e8ad6d3f9b82c1190cbd77e8502f4f763985cefdbe85ed18947fcac9d +size 1962896096 diff --git a/Qwen_Qwen3-4B-Instruct-2507-IQ3_XS.gguf b/Qwen_Qwen3-4B-Instruct-2507-IQ3_XS.gguf new file mode 100644 index 0000000..6273b21 --- /dev/null +++ b/Qwen_Qwen3-4B-Instruct-2507-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8192110d563f7f7bfde15a961c5cc6a86cc8db38f4d83d11f904ae745a2dc411 +size 1814375136 diff --git a/Qwen_Qwen3-4B-Instruct-2507-IQ3_XXS.gguf b/Qwen_Qwen3-4B-Instruct-2507-IQ3_XXS.gguf new file mode 100644 index 0000000..d6405c5 --- /dev/null +++ b/Qwen_Qwen3-4B-Instruct-2507-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbb60c3369dec665b2f922dd027464f1c1e5c1e1af62b48f34d9dc811404c65f +size 1670188256 diff --git a/Qwen_Qwen3-4B-Instruct-2507-IQ4_NL.gguf b/Qwen_Qwen3-4B-Instruct-2507-IQ4_NL.gguf new file mode 100644 index 0000000..95b0b7d --- /dev/null +++ b/Qwen_Qwen3-4B-Instruct-2507-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bcd60be4de4e2423cfa8db4f3207e54602bf85584b97ef364be044bfd9826ac +size 2381343456 diff --git a/Qwen_Qwen3-4B-Instruct-2507-IQ4_XS.gguf b/Qwen_Qwen3-4B-Instruct-2507-IQ4_XS.gguf new file mode 100644 index 0000000..306a027 --- /dev/null +++ b/Qwen_Qwen3-4B-Instruct-2507-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c33ca3b360e1b2f018e31bead52888e83566bb22fc9ef783efa991a00364420d +size 2270751456 diff --git a/Qwen_Qwen3-4B-Instruct-2507-Q2_K.gguf b/Qwen_Qwen3-4B-Instruct-2507-Q2_K.gguf new file mode 100644 index 0000000..c6d6df8 --- /dev/null +++ b/Qwen_Qwen3-4B-Instruct-2507-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f9efe8a86c1d200139801642dcf8c0d9f2cf09c89ef4e8f0ea525536368c4ca +size 1669499616 diff --git a/Qwen_Qwen3-4B-Instruct-2507-Q2_K_L.gguf b/Qwen_Qwen3-4B-Instruct-2507-Q2_K_L.gguf new file mode 100644 index 0000000..24952c2 --- /dev/null +++ b/Qwen_Qwen3-4B-Instruct-2507-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be4d99fbd1139f0b9a9fd44dae65ed0a4523df39112211cf87bbea1a1ac9b842 +size 1763699936 diff --git a/Qwen_Qwen3-4B-Instruct-2507-Q3_K_L.gguf b/Qwen_Qwen3-4B-Instruct-2507-Q3_K_L.gguf new file mode 100644 index 0000000..15a2b73 --- /dev/null +++ b/Qwen_Qwen3-4B-Instruct-2507-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2e1b8c30d2ba9ea7957ae6e201cef5296766281e0fcba100048335c0c799bc5 +size 2239785696 diff --git a/Qwen_Qwen3-4B-Instruct-2507-Q3_K_M.gguf b/Qwen_Qwen3-4B-Instruct-2507-Q3_K_M.gguf new file mode 100644 index 0000000..810349a --- /dev/null +++ b/Qwen_Qwen3-4B-Instruct-2507-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35295e9a0a42eff5ebc592412c754991c0b6cc36bf4f282b2a491b211476752d +size 2075618016 diff --git a/Qwen_Qwen3-4B-Instruct-2507-Q3_K_S.gguf b/Qwen_Qwen3-4B-Instruct-2507-Q3_K_S.gguf new file mode 100644 index 0000000..338954f --- /dev/null +++ b/Qwen_Qwen3-4B-Instruct-2507-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68e5c8cb8ac33cb5b86c1dc31885a772782b42699d144fcfbe353489d9b289db +size 1886997216 diff --git a/Qwen_Qwen3-4B-Instruct-2507-Q3_K_XL.gguf b/Qwen_Qwen3-4B-Instruct-2507-Q3_K_XL.gguf new file mode 100644 index 0000000..fc120f8 --- /dev/null +++ b/Qwen_Qwen3-4B-Instruct-2507-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bd04c2178d45160802b813a0e0cc82553ce84a6db7ed6615aac858f4551415c +size 2333986016 diff --git a/Qwen_Qwen3-4B-Instruct-2507-Q4_0.gguf b/Qwen_Qwen3-4B-Instruct-2507-Q4_0.gguf new file mode 100644 index 0000000..aea4870 --- /dev/null +++ b/Qwen_Qwen3-4B-Instruct-2507-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2198e1e35b98e2e126a00d9e853a53bc3a4bcca5f82cfbf2a03b38a91f2662c +size 2375772896 diff --git a/Qwen_Qwen3-4B-Instruct-2507-Q4_1.gguf b/Qwen_Qwen3-4B-Instruct-2507-Q4_1.gguf new file mode 100644 index 0000000..c53db02 --- /dev/null +++ b/Qwen_Qwen3-4B-Instruct-2507-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c6d59300fe2abd6d68883fe0af72e5b528aa275cd5e8bed7d73ff38ba920f22 +size 2596629216 diff --git a/Qwen_Qwen3-4B-Instruct-2507-Q4_K_L.gguf b/Qwen_Qwen3-4B-Instruct-2507-Q4_K_L.gguf new file mode 100644 index 0000000..2a33ce1 --- /dev/null +++ b/Qwen_Qwen3-4B-Instruct-2507-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:438820a7284cab964b48312bd4750ca35627e5e74dc51d05bd4efa3cb8616d1a +size 2591481056 diff --git a/Qwen_Qwen3-4B-Instruct-2507-Q4_K_M.gguf b/Qwen_Qwen3-4B-Instruct-2507-Q4_K_M.gguf new file mode 100644 index 0000000..c43ec5b --- /dev/null +++ b/Qwen_Qwen3-4B-Instruct-2507-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fde00ce69dd4899c70d020845e2638353015bba0fdf161b3eb965f2bca4464e +size 2497280736 diff --git a/Qwen_Qwen3-4B-Instruct-2507-Q4_K_S.gguf b/Qwen_Qwen3-4B-Instruct-2507-Q4_K_S.gguf new file mode 100644 index 0000000..a9002a7 --- /dev/null +++ b/Qwen_Qwen3-4B-Instruct-2507-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:952af947c6aabf7b72f7d8e279e76f7bf4b0d12431eb3abb588ef312865622d8 +size 2383309536 diff --git a/Qwen_Qwen3-4B-Instruct-2507-Q5_K_L.gguf b/Qwen_Qwen3-4B-Instruct-2507-Q5_K_L.gguf new file mode 100644 index 0000000..dfff3a8 --- /dev/null +++ b/Qwen_Qwen3-4B-Instruct-2507-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:396a1eaba8407efe0ca6d91fc5a9d4e2f64714db64380fd5166ad0005dc1da5d +size 2983714016 diff --git a/Qwen_Qwen3-4B-Instruct-2507-Q5_K_M.gguf b/Qwen_Qwen3-4B-Instruct-2507-Q5_K_M.gguf new file mode 100644 index 0000000..2fcaf49 --- /dev/null +++ b/Qwen_Qwen3-4B-Instruct-2507-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66713ce35a58a82fe87642d4ec13425bf9b9a46800fff5c49a665ef5701439dc +size 2889513696 diff --git a/Qwen_Qwen3-4B-Instruct-2507-Q5_K_S.gguf b/Qwen_Qwen3-4B-Instruct-2507-Q5_K_S.gguf new file mode 100644 index 0000000..ecc9f09 --- /dev/null +++ b/Qwen_Qwen3-4B-Instruct-2507-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c43a3155890ec4543dc5868e3859a2eca19b708bc1efd7bf0c0af3f057268d2 +size 2823711456 diff --git a/Qwen_Qwen3-4B-Instruct-2507-Q6_K.gguf b/Qwen_Qwen3-4B-Instruct-2507-Q6_K.gguf new file mode 100644 index 0000000..1d4ff34 --- /dev/null +++ b/Qwen_Qwen3-4B-Instruct-2507-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:324bcc583feabe9485df2521099bf913e2613048e7aa2bdcdbfe74f1acc7531e +size 3306261216 diff --git a/Qwen_Qwen3-4B-Instruct-2507-Q6_K_L.gguf b/Qwen_Qwen3-4B-Instruct-2507-Q6_K_L.gguf new file mode 100644 index 0000000..f91e8e2 --- /dev/null +++ b/Qwen_Qwen3-4B-Instruct-2507-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3ca50571641ea44bc0c3c63901eb29cc1b641e327242e0a5e5a95690f7ec3c5 +size 3400461536 diff --git a/Qwen_Qwen3-4B-Instruct-2507-Q8_0.gguf b/Qwen_Qwen3-4B-Instruct-2507-Q8_0.gguf new file mode 100644 index 0000000..5c8ff4f --- /dev/null +++ b/Qwen_Qwen3-4B-Instruct-2507-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:260b5b5b6ad73e44df81a43ea1f5c11c37007b6bac18eb3cd2016e8667c19662 +size 4280405216 diff --git a/Qwen_Qwen3-4B-Instruct-2507-bf16.gguf b/Qwen_Qwen3-4B-Instruct-2507-bf16.gguf new file mode 100644 index 0000000..4692692 --- /dev/null +++ b/Qwen_Qwen3-4B-Instruct-2507-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75c31072dd3f6a5f2d3cdf13f1c72f61fddc1dd084b77a50620b289d71521774 +size 8051284928 diff --git a/Qwen_Qwen3-4B-Instruct-2507-imatrix.gguf b/Qwen_Qwen3-4B-Instruct-2507-imatrix.gguf new file mode 100644 index 0000000..10a310a --- /dev/null +++ b/Qwen_Qwen3-4B-Instruct-2507-imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82f4b42f83986c180f866551e24d227bbc5a3aba7263c3282a44580d818b9ce2 +size 3872640 diff --git a/README.md b/README.md new file mode 100644 index 0000000..fc6f1f0 --- /dev/null +++ b/README.md @@ -0,0 +1,170 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +base_model_relation: quantized +base_model: Qwen/Qwen3-4B-Instruct-2507 +--- + +## Llamacpp imatrix Quantizations of Qwen3-4B-Instruct-2507 by Qwen + +Using llama.cpp release b6096 for quantization. + +Original model: https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507 + +All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8) + +Run them in [LM Studio](https://lmstudio.ai/) + +Run them directly with [llama.cpp](https://github.com/ggerganov/llama.cpp), or any other llama.cpp based project + +## Prompt format + +``` +<|im_start|>system +{system_prompt}<|im_end|> +<|im_start|>user +{prompt}<|im_end|> +<|im_start|>assistant +``` + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [Qwen3-4B-Instruct-2507-bf16.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-bf16.gguf) | bf16 | 8.05GB | false | Full BF16 weights. | +| [Qwen3-4B-Instruct-2507-Q8_0.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-Q8_0.gguf) | Q8_0 | 4.28GB | false | Extremely high quality, generally unneeded but max available quant. | +| [Qwen3-4B-Instruct-2507-Q6_K_L.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-Q6_K_L.gguf) | Q6_K_L | 3.40GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [Qwen3-4B-Instruct-2507-Q6_K.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-Q6_K.gguf) | Q6_K | 3.31GB | false | Very high quality, near perfect, *recommended*. | +| [Qwen3-4B-Instruct-2507-Q5_K_L.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-Q5_K_L.gguf) | Q5_K_L | 2.98GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [Qwen3-4B-Instruct-2507-Q5_K_M.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-Q5_K_M.gguf) | Q5_K_M | 2.89GB | false | High quality, *recommended*. | +| [Qwen3-4B-Instruct-2507-Q5_K_S.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-Q5_K_S.gguf) | Q5_K_S | 2.82GB | false | High quality, *recommended*. | +| [Qwen3-4B-Instruct-2507-Q4_1.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-Q4_1.gguf) | Q4_1 | 2.60GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [Qwen3-4B-Instruct-2507-Q4_K_L.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-Q4_K_L.gguf) | Q4_K_L | 2.59GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [Qwen3-4B-Instruct-2507-Q4_K_M.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-Q4_K_M.gguf) | Q4_K_M | 2.50GB | false | Good quality, default size for most use cases, *recommended*. | +| [Qwen3-4B-Instruct-2507-Q4_K_S.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-Q4_K_S.gguf) | Q4_K_S | 2.38GB | false | Slightly lower quality with more space savings, *recommended*. | +| [Qwen3-4B-Instruct-2507-Q4_0.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-Q4_0.gguf) | Q4_0 | 2.38GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [Qwen3-4B-Instruct-2507-IQ4_NL.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-IQ4_NL.gguf) | IQ4_NL | 2.38GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [Qwen3-4B-Instruct-2507-Q3_K_XL.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-Q3_K_XL.gguf) | Q3_K_XL | 2.33GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [Qwen3-4B-Instruct-2507-IQ4_XS.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-IQ4_XS.gguf) | IQ4_XS | 2.27GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [Qwen3-4B-Instruct-2507-Q3_K_L.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-Q3_K_L.gguf) | Q3_K_L | 2.24GB | false | Lower quality but usable, good for low RAM availability. | +| [Qwen3-4B-Instruct-2507-Q3_K_M.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-Q3_K_M.gguf) | Q3_K_M | 2.08GB | false | Low quality. | +| [Qwen3-4B-Instruct-2507-IQ3_M.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-IQ3_M.gguf) | IQ3_M | 1.96GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [Qwen3-4B-Instruct-2507-Q3_K_S.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-Q3_K_S.gguf) | Q3_K_S | 1.89GB | false | Low quality, not recommended. | +| [Qwen3-4B-Instruct-2507-IQ3_XS.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-IQ3_XS.gguf) | IQ3_XS | 1.81GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [Qwen3-4B-Instruct-2507-Q2_K_L.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-Q2_K_L.gguf) | Q2_K_L | 1.76GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [Qwen3-4B-Instruct-2507-IQ3_XXS.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-IQ3_XXS.gguf) | IQ3_XXS | 1.67GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [Qwen3-4B-Instruct-2507-Q2_K.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-Q2_K.gguf) | Q2_K | 1.67GB | false | Very low quality but surprisingly usable. | +| [Qwen3-4B-Instruct-2507-IQ2_M.gguf](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen_Qwen3-4B-Instruct-2507-IQ2_M.gguf) | IQ2_M | 1.51GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. | + +## Embed/output weights + +Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to. + +## Downloading using huggingface-cli + +
+ Click to view download instructions + +First, make sure you have hugginface-cli installed: + +``` +pip install -U "huggingface_hub[cli]" +``` + +Then, you can target the specific file you want: + +``` +huggingface-cli download bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF --include "Qwen_Qwen3-4B-Instruct-2507-Q4_K_M.gguf" --local-dir ./ +``` + +If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run: + +``` +huggingface-cli download bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF --include "Qwen_Qwen3-4B-Instruct-2507-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (Qwen_Qwen3-4B-Instruct-2507-Q8_0) or download them all in place (./) + +
+ +## ARM/AVX information + +Previously, you would download Q4_0_4_4/4_8/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass. + +Now, however, there is something called "online repacking" for weights. details in [this PR](https://github.com/ggerganov/llama.cpp/pull/9921). If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly. + +As of llama.cpp build [b4282](https://github.com/ggerganov/llama.cpp/releases/tag/b4282) you will not be able to run the Q4_0_X_X files and will instead need to use Q4_0. + +Additionally, if you want to get slightly better quality for , you can use IQ4_NL thanks to [this PR](https://github.com/ggerganov/llama.cpp/pull/10541) which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed incrase. + +
+ Click to view Q4_0_X_X information (deprecated + +I'm keeping this section to show the potential theoretical uplift in performance from using the Q4_0 with online repacking. + +
+ Click to view benchmarks on an AVX2 system (EPYC7702) + +| model | size | params | backend | threads | test | t/s | % (vs Q4_0) | +| ------------------------------ | ---------: | ---------: | ---------- | ------: | ------------: | -------------------: |-------------: | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp512 | 204.03 ± 1.03 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp1024 | 282.92 ± 0.19 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp2048 | 259.49 ± 0.44 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg128 | 39.12 ± 0.27 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg256 | 39.31 ± 0.69 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg512 | 40.52 ± 0.03 | 100% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp512 | 301.02 ± 1.74 | 147% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp1024 | 287.23 ± 0.20 | 101% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp2048 | 262.77 ± 1.81 | 101% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg128 | 18.80 ± 0.99 | 48% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg256 | 24.46 ± 3.04 | 83% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg512 | 36.32 ± 3.59 | 90% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp512 | 271.71 ± 3.53 | 133% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp1024 | 279.86 ± 45.63 | 100% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp2048 | 320.77 ± 5.00 | 124% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg128 | 43.51 ± 0.05 | 111% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg256 | 43.35 ± 0.09 | 110% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg512 | 42.60 ± 0.31 | 105% | + +Q4_0_8_8 offers a nice bump to prompt processing and a small bump to text generation + +
+ +
+ +## Which file should I choose? + +
+ Click here for details + +A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9) + +The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have. + +If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM. + +If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total. + +Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'. + +If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M. + +If you want to get more into the weeds, you can check out this extremely useful feature chart: + +[llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix) + +But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size. + +These I-quants can also be used on CPU, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide. + +
+ +## Credits + +Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset. + +Thank you ZeroWw for the inspiration to experiment with embed/output. + +Thank you to LM Studio for sponsoring my work. + +Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file