commit 9b5786fe51e86876c4d6e3f53efd50d7752f8ff5 Author: ModelHub XC Date: Fri Jul 10 00:23:11 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/NVIDIA-Nemotron-3-Nano-4B-BF16-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..dbae56c --- /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 +*.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 +NVIDIA-Nemotron-3-Nano-4B-BF16.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +NVIDIA-Nemotron-3-Nano-4B-BF16.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +NVIDIA-Nemotron-3-Nano-4B-BF16.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +NVIDIA-Nemotron-3-Nano-4B-BF16.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NVIDIA-Nemotron-3-Nano-4B-BF16.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NVIDIA-Nemotron-3-Nano-4B-BF16.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NVIDIA-Nemotron-3-Nano-4B-BF16.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NVIDIA-Nemotron-3-Nano-4B-BF16.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NVIDIA-Nemotron-3-Nano-4B-BF16.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NVIDIA-Nemotron-3-Nano-4B-BF16.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +NVIDIA-Nemotron-3-Nano-4B-BF16.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +NVIDIA-Nemotron-3-Nano-4B-BF16.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/NVIDIA-Nemotron-3-Nano-4B-BF16.IQ4_XS.gguf b/NVIDIA-Nemotron-3-Nano-4B-BF16.IQ4_XS.gguf new file mode 100644 index 0000000..b948548 --- /dev/null +++ b/NVIDIA-Nemotron-3-Nano-4B-BF16.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:044a312c53cf3b326993986262d0a50e33f4aba8ba9fd83352d4a7e5879e2ca7 +size 2445108640 diff --git a/NVIDIA-Nemotron-3-Nano-4B-BF16.Q2_K.gguf b/NVIDIA-Nemotron-3-Nano-4B-BF16.Q2_K.gguf new file mode 100644 index 0000000..53c8096 --- /dev/null +++ b/NVIDIA-Nemotron-3-Nano-4B-BF16.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:670779344a102982ad8f265b5453d2c373c13868eaeb455ba3913240e70d8ef6 +size 2237198112 diff --git a/NVIDIA-Nemotron-3-Nano-4B-BF16.Q3_K_L.gguf b/NVIDIA-Nemotron-3-Nano-4B-BF16.Q3_K_L.gguf new file mode 100644 index 0000000..4f59390 --- /dev/null +++ b/NVIDIA-Nemotron-3-Nano-4B-BF16.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b9c025dab210a14060730ccc618c658bbafa6623e047b85c52c3cfade9a09d1 +size 2479943328 diff --git a/NVIDIA-Nemotron-3-Nano-4B-BF16.Q3_K_M.gguf b/NVIDIA-Nemotron-3-Nano-4B-BF16.Q3_K_M.gguf new file mode 100644 index 0000000..3d2c6be --- /dev/null +++ b/NVIDIA-Nemotron-3-Nano-4B-BF16.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dde17a26334b51d9eb6b4f70cbdecb2ec904bafb3e98a2f93850e64663f9463 +size 2397755040 diff --git a/NVIDIA-Nemotron-3-Nano-4B-BF16.Q3_K_S.gguf b/NVIDIA-Nemotron-3-Nano-4B-BF16.Q3_K_S.gguf new file mode 100644 index 0000000..4f58f36 --- /dev/null +++ b/NVIDIA-Nemotron-3-Nano-4B-BF16.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ccb79d2cc10855b45a4646e3cb501df9bc6a38a0555eae3c1df0c50fceb66c7 +size 2288565792 diff --git a/NVIDIA-Nemotron-3-Nano-4B-BF16.Q4_K_M.gguf b/NVIDIA-Nemotron-3-Nano-4B-BF16.Q4_K_M.gguf new file mode 100644 index 0000000..b4e14db --- /dev/null +++ b/NVIDIA-Nemotron-3-Nano-4B-BF16.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21fc5d6f9047f8484765368bd5945883de140913a534f15c690beaa8ff18e6f6 +size 2837077280 diff --git a/NVIDIA-Nemotron-3-Nano-4B-BF16.Q4_K_S.gguf b/NVIDIA-Nemotron-3-Nano-4B-BF16.Q4_K_S.gguf new file mode 100644 index 0000000..39f5151 --- /dev/null +++ b/NVIDIA-Nemotron-3-Nano-4B-BF16.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6bb819d1fcafe6581a15447fccbe49a9679111ca5daf3011e62ccef5191a2c8 +size 2768781472 diff --git a/NVIDIA-Nemotron-3-Nano-4B-BF16.Q5_K_M.gguf b/NVIDIA-Nemotron-3-Nano-4B-BF16.Q5_K_M.gguf new file mode 100644 index 0000000..220905a --- /dev/null +++ b/NVIDIA-Nemotron-3-Nano-4B-BF16.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:298bbef91c0b2a34658a0e878816afdd6e749155c4c6f5934212061c1fb3bc29 +size 3092416672 diff --git a/NVIDIA-Nemotron-3-Nano-4B-BF16.Q5_K_S.gguf b/NVIDIA-Nemotron-3-Nano-4B-BF16.Q5_K_S.gguf new file mode 100644 index 0000000..fe81754 --- /dev/null +++ b/NVIDIA-Nemotron-3-Nano-4B-BF16.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce80488867efcdeccdadcc556b7e55c5f137af88c0a1c785ac9f4ebc0041c3b7 +size 3043388448 diff --git a/NVIDIA-Nemotron-3-Nano-4B-BF16.Q6_K.gguf b/NVIDIA-Nemotron-3-Nano-4B-BF16.Q6_K.gguf new file mode 100644 index 0000000..6dfe8ed --- /dev/null +++ b/NVIDIA-Nemotron-3-Nano-4B-BF16.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d44b738bd52d4bf1a406236f90fb57129a82e1fa4c6ca13f7682f1335c395cd +size 3933673760 diff --git a/NVIDIA-Nemotron-3-Nano-4B-BF16.Q8_0.gguf b/NVIDIA-Nemotron-3-Nano-4B-BF16.Q8_0.gguf new file mode 100644 index 0000000..3efc81a --- /dev/null +++ b/NVIDIA-Nemotron-3-Nano-4B-BF16.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5de125991307ec3e3657a3dba67ec6e9c84d4c5a4d02155a1e750552745951a +size 4233682336 diff --git a/NVIDIA-Nemotron-3-Nano-4B-BF16.f16.gguf b/NVIDIA-Nemotron-3-Nano-4B-BF16.f16.gguf new file mode 100644 index 0000000..123ffa7 --- /dev/null +++ b/NVIDIA-Nemotron-3-Nano-4B-BF16.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:878bbbde8ce09dfb35fcc9cda6215c42c37d63b7b01e06f209ba93e8425553af +size 7957650976 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e9b94d4 --- /dev/null +++ b/README.md @@ -0,0 +1,89 @@ +--- +base_model: nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16 +datasets: +- nvidia/Nemotron-CC-v2 +- nvidia/Nemotron-Post-Training-Dataset-v2 +- nvidia/Nemotron-Science-v1 +- nvidia/Nemotron-Instruction-Following-Chat-v1 +- nvidia/Nemotron-Agentic-v1 +- nvidia/Nemotron-Competitive-Programming-v1 +- nvidia/Nemotron-Math-Proofs-v1 +- nvidia/Nemotron-RL-Agentic-Conversational-Tool-Use-Pivot-v1 +- nvidia/Nemotron-RL-instruction_following +- nvidia/Nemotron-RL-agent-calendar_scheduling +- nvidia/Nemotron-RL-instruction_following-structured_outputs +language: +- en +library_name: transformers +license: other +license_link: https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-nemotron-open-model-license/ +license_name: nvidia-nemotron-open-model-license +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- nvidia +- pytorch +--- +## About + + + + + + + + + +static quants of https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#NVIDIA-Nemotron-3-Nano-4B-BF16-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/NVIDIA-Nemotron-3-Nano-4B-BF16-i1-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/NVIDIA-Nemotron-3-Nano-4B-BF16-GGUF/resolve/main/NVIDIA-Nemotron-3-Nano-4B-BF16.Q2_K.gguf) | Q2_K | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/NVIDIA-Nemotron-3-Nano-4B-BF16-GGUF/resolve/main/NVIDIA-Nemotron-3-Nano-4B-BF16.Q3_K_S.gguf) | Q3_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/NVIDIA-Nemotron-3-Nano-4B-BF16-GGUF/resolve/main/NVIDIA-Nemotron-3-Nano-4B-BF16.Q3_K_M.gguf) | Q3_K_M | 2.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/NVIDIA-Nemotron-3-Nano-4B-BF16-GGUF/resolve/main/NVIDIA-Nemotron-3-Nano-4B-BF16.IQ4_XS.gguf) | IQ4_XS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/NVIDIA-Nemotron-3-Nano-4B-BF16-GGUF/resolve/main/NVIDIA-Nemotron-3-Nano-4B-BF16.Q3_K_L.gguf) | Q3_K_L | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/NVIDIA-Nemotron-3-Nano-4B-BF16-GGUF/resolve/main/NVIDIA-Nemotron-3-Nano-4B-BF16.Q4_K_S.gguf) | Q4_K_S | 2.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NVIDIA-Nemotron-3-Nano-4B-BF16-GGUF/resolve/main/NVIDIA-Nemotron-3-Nano-4B-BF16.Q4_K_M.gguf) | Q4_K_M | 2.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NVIDIA-Nemotron-3-Nano-4B-BF16-GGUF/resolve/main/NVIDIA-Nemotron-3-Nano-4B-BF16.Q5_K_S.gguf) | Q5_K_S | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/NVIDIA-Nemotron-3-Nano-4B-BF16-GGUF/resolve/main/NVIDIA-Nemotron-3-Nano-4B-BF16.Q5_K_M.gguf) | Q5_K_M | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/NVIDIA-Nemotron-3-Nano-4B-BF16-GGUF/resolve/main/NVIDIA-Nemotron-3-Nano-4B-BF16.Q6_K.gguf) | Q6_K | 4.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/NVIDIA-Nemotron-3-Nano-4B-BF16-GGUF/resolve/main/NVIDIA-Nemotron-3-Nano-4B-BF16.Q8_0.gguf) | Q8_0 | 4.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/NVIDIA-Nemotron-3-Nano-4B-BF16-GGUF/resolve/main/NVIDIA-Nemotron-3-Nano-4B-BF16.f16.gguf) | f16 | 8.1 | 16 bpw, overkill | + +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. + +