commit 2d325869f98d5f10dabd933d21208656bc4df9bf Author: ModelHub XC Date: Thu Jul 23 07:18:06 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/HuggingFaceTB_SmolLM3-3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d16a1c5 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,71 @@ +*.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 +HuggingFaceTB_SmolLM3-3B-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +HuggingFaceTB_SmolLM3-3B-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +HuggingFaceTB_SmolLM3-3B-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +HuggingFaceTB_SmolLM3-3B-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +HuggingFaceTB_SmolLM3-3B-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +HuggingFaceTB_SmolLM3-3B-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +HuggingFaceTB_SmolLM3-3B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +HuggingFaceTB_SmolLM3-3B-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text +HuggingFaceTB_SmolLM3-3B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +HuggingFaceTB_SmolLM3-3B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +HuggingFaceTB_SmolLM3-3B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +HuggingFaceTB_SmolLM3-3B-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +HuggingFaceTB_SmolLM3-3B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +HuggingFaceTB_SmolLM3-3B-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +HuggingFaceTB_SmolLM3-3B-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text +HuggingFaceTB_SmolLM3-3B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +HuggingFaceTB_SmolLM3-3B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +HuggingFaceTB_SmolLM3-3B-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text +HuggingFaceTB_SmolLM3-3B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +HuggingFaceTB_SmolLM3-3B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +HuggingFaceTB_SmolLM3-3B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +HuggingFaceTB_SmolLM3-3B-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text +HuggingFaceTB_SmolLM3-3B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +HuggingFaceTB_SmolLM3-3B-bf16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/HuggingFaceTB_SmolLM3-3B-IQ2_M.gguf b/HuggingFaceTB_SmolLM3-3B-IQ2_M.gguf new file mode 100644 index 0000000..a4ba543 --- /dev/null +++ b/HuggingFaceTB_SmolLM3-3B-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96b88ac2f3b0e7fe336c80e22feafce9f99ffc0ff8f5780f949eb1124808b7b6 +size 1125355328 diff --git a/HuggingFaceTB_SmolLM3-3B-IQ3_M.gguf b/HuggingFaceTB_SmolLM3-3B-IQ3_M.gguf new file mode 100644 index 0000000..d83683d --- /dev/null +++ b/HuggingFaceTB_SmolLM3-3B-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddce138598e1f963e626334658d7a082d65fce70336d82e3e3eb1039c95d72d5 +size 1469357888 diff --git a/HuggingFaceTB_SmolLM3-3B-IQ3_XS.gguf b/HuggingFaceTB_SmolLM3-3B-IQ3_XS.gguf new file mode 100644 index 0000000..25cd0d7 --- /dev/null +++ b/HuggingFaceTB_SmolLM3-3B-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4e9d926ddef9ad235269c0460be583d885c0b09ba2ce11affc38ff42c583223 +size 1371414336 diff --git a/HuggingFaceTB_SmolLM3-3B-IQ3_XXS.gguf b/HuggingFaceTB_SmolLM3-3B-IQ3_XXS.gguf new file mode 100644 index 0000000..e9186c3 --- /dev/null +++ b/HuggingFaceTB_SmolLM3-3B-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:356b83c016a7613e79791c2c86acea765f672afa1e18d206377e8118cff41ab7 +size 1267666752 diff --git a/HuggingFaceTB_SmolLM3-3B-IQ4_NL.gguf b/HuggingFaceTB_SmolLM3-3B-IQ4_NL.gguf new file mode 100644 index 0000000..8d8c3a3 --- /dev/null +++ b/HuggingFaceTB_SmolLM3-3B-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af5e551b726a81b52bc06d7d9395f82890a326e36d814f03112fb0f9f41cfafe +size 1810538304 diff --git a/HuggingFaceTB_SmolLM3-3B-IQ4_XS.gguf b/HuggingFaceTB_SmolLM3-3B-IQ4_XS.gguf new file mode 100644 index 0000000..f15f5dd --- /dev/null +++ b/HuggingFaceTB_SmolLM3-3B-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:342fe3669e6db39bf9b9b514923f2af4a7d6b069efb45cc8f583cfc31cb75553 +size 1723834176 diff --git a/HuggingFaceTB_SmolLM3-3B-Q2_K.gguf b/HuggingFaceTB_SmolLM3-3B-Q2_K.gguf new file mode 100644 index 0000000..aa7f48e --- /dev/null +++ b/HuggingFaceTB_SmolLM3-3B-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:794509645d684d6b563b054c312f502af793e040155080d4de358e698f638354 +size 1253302080 diff --git a/HuggingFaceTB_SmolLM3-3B-Q2_K_L.gguf b/HuggingFaceTB_SmolLM3-3B-Q2_K_L.gguf new file mode 100644 index 0000000..f5a3763 --- /dev/null +++ b/HuggingFaceTB_SmolLM3-3B-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27a3fbb59204030c2146452c193c12d946df13bd614b3f2131012adb4bf61ea5 +size 1316917056 diff --git a/HuggingFaceTB_SmolLM3-3B-Q3_K_L.gguf b/HuggingFaceTB_SmolLM3-3B-Q3_K_L.gguf new file mode 100644 index 0000000..c0c65d4 --- /dev/null +++ b/HuggingFaceTB_SmolLM3-3B-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e93d6464243fb3d809fcceaba79f1ceef02637ea61ad532af4ea95bc6fb7507 +size 1690214208 diff --git a/HuggingFaceTB_SmolLM3-3B-Q3_K_M.gguf b/HuggingFaceTB_SmolLM3-3B-Q3_K_M.gguf new file mode 100644 index 0000000..3311e8c --- /dev/null +++ b/HuggingFaceTB_SmolLM3-3B-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e5c70fdc3429023ed88ead8af2a70684047e2628258b650bdb729c8437639d0 +size 1571069760 diff --git a/HuggingFaceTB_SmolLM3-3B-Q3_K_S.gguf b/HuggingFaceTB_SmolLM3-3B-Q3_K_S.gguf new file mode 100644 index 0000000..01cb54e --- /dev/null +++ b/HuggingFaceTB_SmolLM3-3B-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40e2c50e950947363e3222353407dc407fad8c0bb03314d8b2278966b7d508aa +size 1432313664 diff --git a/HuggingFaceTB_SmolLM3-3B-Q3_K_XL.gguf b/HuggingFaceTB_SmolLM3-3B-Q3_K_XL.gguf new file mode 100644 index 0000000..a667709 --- /dev/null +++ b/HuggingFaceTB_SmolLM3-3B-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07660c5582bf9b26e7558f8a83723cf4a60665340db9276fee435d8586d4091a +size 1753829184 diff --git a/HuggingFaceTB_SmolLM3-3B-Q4_0.gguf b/HuggingFaceTB_SmolLM3-3B-Q4_0.gguf new file mode 100644 index 0000000..b1b027e --- /dev/null +++ b/HuggingFaceTB_SmolLM3-3B-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e0e56d458e6b6d5ea18d0e5fe598cca252450308f1648afab49984fceae47da +size 1811455808 diff --git a/HuggingFaceTB_SmolLM3-3B-Q4_1.gguf b/HuggingFaceTB_SmolLM3-3B-Q4_1.gguf new file mode 100644 index 0000000..7088913 --- /dev/null +++ b/HuggingFaceTB_SmolLM3-3B-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2603ac4acb987b702fb45bb439e752313a63fe02ae6f9b837cf7ef075e77a1a3 +size 1981587264 diff --git a/HuggingFaceTB_SmolLM3-3B-Q4_K_L.gguf b/HuggingFaceTB_SmolLM3-3B-Q4_K_L.gguf new file mode 100644 index 0000000..241af2d --- /dev/null +++ b/HuggingFaceTB_SmolLM3-3B-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6ee0b21fff62763bae1d7ce829b5e22f92e06e7560a809b0f22d0e7347cc491 +size 1978920768 diff --git a/HuggingFaceTB_SmolLM3-3B-Q4_K_M.gguf b/HuggingFaceTB_SmolLM3-3B-Q4_K_M.gguf new file mode 100644 index 0000000..62302d6 --- /dev/null +++ b/HuggingFaceTB_SmolLM3-3B-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:519732558d5fa7420ab058e1b776dcfe73da78013c2fe59c7ca43c325ef89132 +size 1915305792 diff --git a/HuggingFaceTB_SmolLM3-3B-Q4_K_S.gguf b/HuggingFaceTB_SmolLM3-3B-Q4_K_S.gguf new file mode 100644 index 0000000..7f6b007 --- /dev/null +++ b/HuggingFaceTB_SmolLM3-3B-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1df314cf8900f93d02628430c1325872bb355f9258f858b966fed2aaff2df28 +size 1817616192 diff --git a/HuggingFaceTB_SmolLM3-3B-Q5_K_L.gguf b/HuggingFaceTB_SmolLM3-3B-Q5_K_L.gguf new file mode 100644 index 0000000..c9ef448 --- /dev/null +++ b/HuggingFaceTB_SmolLM3-3B-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:151d2efab4d8d7fbbdb8bd2653b9cb322ed44f937c27dd2f3e328411644a0b7d +size 2277371712 diff --git a/HuggingFaceTB_SmolLM3-3B-Q5_K_M.gguf b/HuggingFaceTB_SmolLM3-3B-Q5_K_M.gguf new file mode 100644 index 0000000..f05c14f --- /dev/null +++ b/HuggingFaceTB_SmolLM3-3B-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65a6490c29a728d1bde5b6a6858418715e773e061433386dbbc39b3f0a088f3d +size 2213756736 diff --git a/HuggingFaceTB_SmolLM3-3B-Q5_K_S.gguf b/HuggingFaceTB_SmolLM3-3B-Q5_K_S.gguf new file mode 100644 index 0000000..44e211e --- /dev/null +++ b/HuggingFaceTB_SmolLM3-3B-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bcedb1cd1b6a4a19075295fdfecffa5b324db58101b5806c10cabd3c7ffedbe +size 2157354816 diff --git a/HuggingFaceTB_SmolLM3-3B-Q6_K.gguf b/HuggingFaceTB_SmolLM3-3B-Q6_K.gguf new file mode 100644 index 0000000..c4d6cfb --- /dev/null +++ b/HuggingFaceTB_SmolLM3-3B-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c7ad22be780006817f727c8a8c0fdc75d35f995c6a91e0210a931cbb20ba6fd +size 2530860864 diff --git a/HuggingFaceTB_SmolLM3-3B-Q6_K_L.gguf b/HuggingFaceTB_SmolLM3-3B-Q6_K_L.gguf new file mode 100644 index 0000000..73c76c6 --- /dev/null +++ b/HuggingFaceTB_SmolLM3-3B-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:406c5a1985fd5be91b865c6945a27ce28b5104dca338f042c0bd7f7f7cfe6175 +size 2594475840 diff --git a/HuggingFaceTB_SmolLM3-3B-Q8_0.gguf b/HuggingFaceTB_SmolLM3-3B-Q8_0.gguf new file mode 100644 index 0000000..1b4bf75 --- /dev/null +++ b/HuggingFaceTB_SmolLM3-3B-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32056df2ec827a1f7c14b6b7f48239fe1d288aba086c811c96a61a8c9df6c733 +size 3275575104 diff --git a/HuggingFaceTB_SmolLM3-3B-bf16.gguf b/HuggingFaceTB_SmolLM3-3B-bf16.gguf new file mode 100644 index 0000000..d51ce55 --- /dev/null +++ b/HuggingFaceTB_SmolLM3-3B-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66a39ad173171c36bce86769449f8db61c062689f964a032995976d20b8245f9 +size 6158339616 diff --git a/HuggingFaceTB_SmolLM3-3B.imatrix b/HuggingFaceTB_SmolLM3-3B.imatrix new file mode 100644 index 0000000..edb03ed Binary files /dev/null and b/HuggingFaceTB_SmolLM3-3B.imatrix differ diff --git a/README.md b/README.md new file mode 100644 index 0000000..da58325 --- /dev/null +++ b/README.md @@ -0,0 +1,195 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +base_model: HuggingFaceTB/SmolLM3-3B +base_model_relation: quantized +license: apache-2.0 +language: +- en +- fr +- es +- it +- pt +- zh +- ar +- ru +--- + +## Llamacpp imatrix Quantizations of SmolLM3-3B by HuggingFaceTB + +Using llama.cpp release b5856 for quantization. + +Original model: https://huggingface.co/HuggingFaceTB/SmolLM3-3B + +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 + +No chat template specified so default is used. This may be incorrect, check original model card for details. + +``` +<|im_start|>system +## Metadata + +Knowledge Cutoff Date: June 2025 +Today Date: 09 July 2025 +Reasoning Mode: /think + +## Custom Instructions + +{system_prompt} + +<|im_start|>user +{prompt}<|im_end|> +<|im_start|>assistant +``` + +## What's new: + +Fix chat template + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [SmolLM3-3B-bf16.gguf](https://huggingface.co/bartowski/HuggingFaceTB_SmolLM3-3B-GGUF/blob/main/HuggingFaceTB_SmolLM3-3B-bf16.gguf) | bf16 | 6.16GB | false | Full BF16 weights. | +| [SmolLM3-3B-Q8_0.gguf](https://huggingface.co/bartowski/HuggingFaceTB_SmolLM3-3B-GGUF/blob/main/HuggingFaceTB_SmolLM3-3B-Q8_0.gguf) | Q8_0 | 3.28GB | false | Extremely high quality, generally unneeded but max available quant. | +| [SmolLM3-3B-Q6_K_L.gguf](https://huggingface.co/bartowski/HuggingFaceTB_SmolLM3-3B-GGUF/blob/main/HuggingFaceTB_SmolLM3-3B-Q6_K_L.gguf) | Q6_K_L | 2.59GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [SmolLM3-3B-Q6_K.gguf](https://huggingface.co/bartowski/HuggingFaceTB_SmolLM3-3B-GGUF/blob/main/HuggingFaceTB_SmolLM3-3B-Q6_K.gguf) | Q6_K | 2.53GB | false | Very high quality, near perfect, *recommended*. | +| [SmolLM3-3B-Q5_K_L.gguf](https://huggingface.co/bartowski/HuggingFaceTB_SmolLM3-3B-GGUF/blob/main/HuggingFaceTB_SmolLM3-3B-Q5_K_L.gguf) | Q5_K_L | 2.28GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [SmolLM3-3B-Q5_K_M.gguf](https://huggingface.co/bartowski/HuggingFaceTB_SmolLM3-3B-GGUF/blob/main/HuggingFaceTB_SmolLM3-3B-Q5_K_M.gguf) | Q5_K_M | 2.21GB | false | High quality, *recommended*. | +| [SmolLM3-3B-Q5_K_S.gguf](https://huggingface.co/bartowski/HuggingFaceTB_SmolLM3-3B-GGUF/blob/main/HuggingFaceTB_SmolLM3-3B-Q5_K_S.gguf) | Q5_K_S | 2.16GB | false | High quality, *recommended*. | +| [SmolLM3-3B-Q4_K_L.gguf](https://huggingface.co/bartowski/HuggingFaceTB_SmolLM3-3B-GGUF/blob/main/HuggingFaceTB_SmolLM3-3B-Q4_K_L.gguf) | Q4_K_L | 1.98GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [SmolLM3-3B-Q4_1.gguf](https://huggingface.co/bartowski/HuggingFaceTB_SmolLM3-3B-GGUF/blob/main/HuggingFaceTB_SmolLM3-3B-Q4_1.gguf) | Q4_1 | 1.98GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [SmolLM3-3B-Q4_K_M.gguf](https://huggingface.co/bartowski/HuggingFaceTB_SmolLM3-3B-GGUF/blob/main/HuggingFaceTB_SmolLM3-3B-Q4_K_M.gguf) | Q4_K_M | 1.92GB | false | Good quality, default size for most use cases, *recommended*. | +| [SmolLM3-3B-Q4_K_S.gguf](https://huggingface.co/bartowski/HuggingFaceTB_SmolLM3-3B-GGUF/blob/main/HuggingFaceTB_SmolLM3-3B-Q4_K_S.gguf) | Q4_K_S | 1.82GB | false | Slightly lower quality with more space savings, *recommended*. | +| [SmolLM3-3B-Q4_0.gguf](https://huggingface.co/bartowski/HuggingFaceTB_SmolLM3-3B-GGUF/blob/main/HuggingFaceTB_SmolLM3-3B-Q4_0.gguf) | Q4_0 | 1.81GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [SmolLM3-3B-IQ4_NL.gguf](https://huggingface.co/bartowski/HuggingFaceTB_SmolLM3-3B-GGUF/blob/main/HuggingFaceTB_SmolLM3-3B-IQ4_NL.gguf) | IQ4_NL | 1.81GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [SmolLM3-3B-Q3_K_XL.gguf](https://huggingface.co/bartowski/HuggingFaceTB_SmolLM3-3B-GGUF/blob/main/HuggingFaceTB_SmolLM3-3B-Q3_K_XL.gguf) | Q3_K_XL | 1.75GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [SmolLM3-3B-IQ4_XS.gguf](https://huggingface.co/bartowski/HuggingFaceTB_SmolLM3-3B-GGUF/blob/main/HuggingFaceTB_SmolLM3-3B-IQ4_XS.gguf) | IQ4_XS | 1.72GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [SmolLM3-3B-Q3_K_L.gguf](https://huggingface.co/bartowski/HuggingFaceTB_SmolLM3-3B-GGUF/blob/main/HuggingFaceTB_SmolLM3-3B-Q3_K_L.gguf) | Q3_K_L | 1.69GB | false | Lower quality but usable, good for low RAM availability. | +| [SmolLM3-3B-Q3_K_M.gguf](https://huggingface.co/bartowski/HuggingFaceTB_SmolLM3-3B-GGUF/blob/main/HuggingFaceTB_SmolLM3-3B-Q3_K_M.gguf) | Q3_K_M | 1.57GB | false | Low quality. | +| [SmolLM3-3B-IQ3_M.gguf](https://huggingface.co/bartowski/HuggingFaceTB_SmolLM3-3B-GGUF/blob/main/HuggingFaceTB_SmolLM3-3B-IQ3_M.gguf) | IQ3_M | 1.47GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [SmolLM3-3B-Q3_K_S.gguf](https://huggingface.co/bartowski/HuggingFaceTB_SmolLM3-3B-GGUF/blob/main/HuggingFaceTB_SmolLM3-3B-Q3_K_S.gguf) | Q3_K_S | 1.43GB | false | Low quality, not recommended. | +| [SmolLM3-3B-IQ3_XS.gguf](https://huggingface.co/bartowski/HuggingFaceTB_SmolLM3-3B-GGUF/blob/main/HuggingFaceTB_SmolLM3-3B-IQ3_XS.gguf) | IQ3_XS | 1.37GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [SmolLM3-3B-Q2_K_L.gguf](https://huggingface.co/bartowski/HuggingFaceTB_SmolLM3-3B-GGUF/blob/main/HuggingFaceTB_SmolLM3-3B-Q2_K_L.gguf) | Q2_K_L | 1.32GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [SmolLM3-3B-IQ3_XXS.gguf](https://huggingface.co/bartowski/HuggingFaceTB_SmolLM3-3B-GGUF/blob/main/HuggingFaceTB_SmolLM3-3B-IQ3_XXS.gguf) | IQ3_XXS | 1.27GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [SmolLM3-3B-Q2_K.gguf](https://huggingface.co/bartowski/HuggingFaceTB_SmolLM3-3B-GGUF/blob/main/HuggingFaceTB_SmolLM3-3B-Q2_K.gguf) | Q2_K | 1.25GB | false | Very low quality but surprisingly usable. | +| [SmolLM3-3B-IQ2_M.gguf](https://huggingface.co/bartowski/HuggingFaceTB_SmolLM3-3B-GGUF/blob/main/HuggingFaceTB_SmolLM3-3B-IQ2_M.gguf) | IQ2_M | 1.13GB | 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/HuggingFaceTB_SmolLM3-3B-GGUF --include "HuggingFaceTB_SmolLM3-3B-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/HuggingFaceTB_SmolLM3-3B-GGUF --include "HuggingFaceTB_SmolLM3-3B-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (HuggingFaceTB_SmolLM3-3B-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