commit 30179cf2f5d2ae9e0b9ef49ae181721b7d1129f8 Author: ModelHub XC Date: Wed Oct 14 23:54:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/OpenCodeReasoning-Nemotron-1.1-14B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d601b97 --- /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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-14B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-14B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-14B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-14B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-14B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-14B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-14B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-14B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-14B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-14B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-14B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-14B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ1_M.gguf b/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ1_M.gguf new file mode 100644 index 0000000..9b4e200 --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a927e52ae1757ccff7f2f0ace7081e2f89d21bedc2dfdee4a298faf45875aa3 +size 3872309984 diff --git a/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ1_S.gguf b/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ1_S.gguf new file mode 100644 index 0000000..2adca48 --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb5ec85a90292644bdaade6f363a686fd64a8674b9179095c949a6a0ae5f0177 +size 3607995104 diff --git a/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ2_M.gguf b/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ2_M.gguf new file mode 100644 index 0000000..b664b64 --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40d6e7611a6286f46431f6e40d40a455da2f322d56a18e4fe1e4485f570bcd90 +size 5356147424 diff --git a/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ2_S.gguf b/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ2_S.gguf new file mode 100644 index 0000000..cc3c7e7 --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1715d9b53dafaf8ff342fc952d24c17eaf570f2a2a4fbfc94ef55d63fcf44d1d +size 5003727584 diff --git a/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ2_XS.gguf b/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..0af5155 --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9b59459a46aacddba41c0dfab07aee705bf78d5494264cf48c92399b85e9213 +size 4704576224 diff --git a/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ2_XXS.gguf b/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..6b48d50 --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:856d51b17ddca5aafaa4ebdaac172ae9bc32d6a608b9d69314c00422bf9eaf33 +size 4312834784 diff --git a/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ3_M.gguf b/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ3_M.gguf new file mode 100644 index 0000000..aa694b3 --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78553f525a99beaf9fda11287387636bf97c53bcc32d3fb3e4cad3817a4460b7 +size 6916539104 diff --git a/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ3_S.gguf b/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ3_S.gguf new file mode 100644 index 0000000..6bf3de3 --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edd5db34aedfd4886d1ace7435202d0c349c2a4c06915b0bef705e70aaf2fdcf +size 6693020384 diff --git a/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ3_XS.gguf b/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..bd6b897 --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:faa0a76fccadbeb89a56f6096df6cc99bd79eec61fccb2e90aefa1c6c8bd7a18 +size 6383362784 diff --git a/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ3_XXS.gguf b/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..b5e1d0b --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df69968e2c7252a14701189f3706df70e792f38e3278363ef6d9e1712a366749 +size 5946708704 diff --git a/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ4_NL.gguf b/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ4_NL.gguf new file mode 100644 index 0000000..63f5cbf --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0264dc406464d7e9b4c1e14ea496f7ada795fb3d0ec96c9b94ecfcf88b45ac21 +size 8549184224 diff --git a/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ4_XS.gguf b/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..12b009b --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7c80c184fcc14ea749047a3dfc01da2e327a8e6cdc75a818837ff2bc8ec9b16 +size 8119841504 diff --git a/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q2_K.gguf b/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q2_K.gguf new file mode 100644 index 0000000..a5fd6d8 --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b00301910bfc8a1806aefab144305690c4b952e59e075c5f0b5b40c3272c1750 +size 5770498784 diff --git a/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q2_K_S.gguf b/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..bcd1ffb --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1750921f7845b10d9166e84f4100b85873106c392c1c0953e31ef8a94b828665 +size 5397189344 diff --git a/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q3_K_L.gguf b/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..83135f4 --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14acf963e1fe757b4c5e0eda81c843411973496914d6c5d89438d4cce28cd268 +size 7924769504 diff --git a/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q3_K_M.gguf b/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..db6c9eb --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3e6a617c4bd2583a6b233862e611d17431950caee50b36d97f552ed4109d712 +size 7339205344 diff --git a/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q3_K_S.gguf b/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..49dbdc1 --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d65f9713eddb66c5453b063aafbf2f9e9104ffd7d9a8293b38af2bec8ad02bb +size 6659597024 diff --git a/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q4_0.gguf b/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q4_0.gguf new file mode 100644 index 0000000..76e5cab --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ec3b54567ec5321da6ecf7b177cbd2032ae556dda81e18a0d02aa142497ef5f +size 8544269024 diff --git a/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q4_1.gguf b/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q4_1.gguf new file mode 100644 index 0000000..a4f569d --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d92114467773158c50d9ff1295affba273127bd7b6c5cd6652108c09c8adac3 +size 9392141024 diff --git a/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q4_K_M.gguf b/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..3d102b3 --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d74e1720250eeb05c4f46b036a011699c0fa89c2a2808c326ac852035f13419e +size 8988111584 diff --git a/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q4_K_S.gguf b/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..9dcacec --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2966e0f7c9bd483b189f34177d9f198746848e1f372da7f97b9dc5c1da5acd58 +size 8573432544 diff --git a/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q5_K_M.gguf b/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..270e2e3 --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17dc567f50319d74d50e7fe6e5be46c578683ed8dee2d53ee7537ffdbca6b880 +size 10508874464 diff --git a/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q5_K_S.gguf b/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..25cc6b7 --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a469571135bf4b362ccc844c1a98d81b41ec4ada1c748a30056ef82543849b4 +size 10266555104 diff --git a/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q6_K.gguf b/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q6_K.gguf new file mode 100644 index 0000000..df69e04 --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3338005b02425a74dee4c6a00765728fc3afdb193de74484175a1feb8c4320c2 +size 12124685024 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1c66bc4 --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: nvidia/OpenCodeReasoning-Nemotron-1.1-14B +datasets: +- nvidia/OpenCodeReasoning +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- nvidia +- code +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/nvidia/OpenCodeReasoning-Nemotron-1.1-14B + + +static quants are available at https://huggingface.co/mradermacher/OpenCodeReasoning-Nemotron-1.1-14B-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/OpenCodeReasoning-Nemotron-1.1-14B-i1-GGUF/resolve/main/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ1_S.gguf) | i1-IQ1_S | 3.7 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/OpenCodeReasoning-Nemotron-1.1-14B-i1-GGUF/resolve/main/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ1_M.gguf) | i1-IQ1_M | 4.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/OpenCodeReasoning-Nemotron-1.1-14B-i1-GGUF/resolve/main/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/OpenCodeReasoning-Nemotron-1.1-14B-i1-GGUF/resolve/main/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/OpenCodeReasoning-Nemotron-1.1-14B-i1-GGUF/resolve/main/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ2_S.gguf) | i1-IQ2_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/OpenCodeReasoning-Nemotron-1.1-14B-i1-GGUF/resolve/main/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ2_M.gguf) | i1-IQ2_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/OpenCodeReasoning-Nemotron-1.1-14B-i1-GGUF/resolve/main/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 5.5 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/OpenCodeReasoning-Nemotron-1.1-14B-i1-GGUF/resolve/main/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q2_K.gguf) | i1-Q2_K | 5.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/OpenCodeReasoning-Nemotron-1.1-14B-i1-GGUF/resolve/main/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 6.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/OpenCodeReasoning-Nemotron-1.1-14B-i1-GGUF/resolve/main/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 6.5 | | +| [GGUF](https://huggingface.co/mradermacher/OpenCodeReasoning-Nemotron-1.1-14B-i1-GGUF/resolve/main/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 6.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/OpenCodeReasoning-Nemotron-1.1-14B-i1-GGUF/resolve/main/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ3_S.gguf) | i1-IQ3_S | 6.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/OpenCodeReasoning-Nemotron-1.1-14B-i1-GGUF/resolve/main/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ3_M.gguf) | i1-IQ3_M | 7.0 | | +| [GGUF](https://huggingface.co/mradermacher/OpenCodeReasoning-Nemotron-1.1-14B-i1-GGUF/resolve/main/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 7.4 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/OpenCodeReasoning-Nemotron-1.1-14B-i1-GGUF/resolve/main/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 8.0 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/OpenCodeReasoning-Nemotron-1.1-14B-i1-GGUF/resolve/main/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 8.2 | | +| [GGUF](https://huggingface.co/mradermacher/OpenCodeReasoning-Nemotron-1.1-14B-i1-GGUF/resolve/main/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q4_0.gguf) | i1-Q4_0 | 8.6 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/OpenCodeReasoning-Nemotron-1.1-14B-i1-GGUF/resolve/main/OpenCodeReasoning-Nemotron-1.1-14B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 8.6 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/OpenCodeReasoning-Nemotron-1.1-14B-i1-GGUF/resolve/main/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 8.7 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/OpenCodeReasoning-Nemotron-1.1-14B-i1-GGUF/resolve/main/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 9.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OpenCodeReasoning-Nemotron-1.1-14B-i1-GGUF/resolve/main/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q4_1.gguf) | i1-Q4_1 | 9.5 | | +| [GGUF](https://huggingface.co/mradermacher/OpenCodeReasoning-Nemotron-1.1-14B-i1-GGUF/resolve/main/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 10.4 | | +| [GGUF](https://huggingface.co/mradermacher/OpenCodeReasoning-Nemotron-1.1-14B-i1-GGUF/resolve/main/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 10.6 | | +| [GGUF](https://huggingface.co/mradermacher/OpenCodeReasoning-Nemotron-1.1-14B-i1-GGUF/resolve/main/OpenCodeReasoning-Nemotron-1.1-14B.i1-Q6_K.gguf) | i1-Q6_K | 12.2 | 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..9b1ebb3 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a8429c3b624b742a69fe02f3e809b523bde858658fdb501dfcb021497e6c99c +size 8563597