---

license: other

license_name: nvidia-nemotron-open-model-license

license_link: https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-nemotron-open-model-license/

base_model:

• nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16

base_model_relation: quantized

library_name: gguf

pipeline_tag: text-generation

tags:

• wekala
• gguf

---

nemotron-3-nano-4b-gguf

Consumer-supplied Wekala model-library assets derived from the attributed official publisher. Models and this repository are distributed separately from the Wekala SDK.

Origin and licence

| Field | Value |

| --- | --- |

| Original developer | NVIDIA Corporation |

| Original model | nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16 |

| Pinned source revision | dfaf35de3e30f1867dd8dbc38a7fc9fb52d3914f |

| Original publication | 2026-03-16 (day) |

| Date evidence | Publisher source |

| Licence | nvidia-nemotron-open-model-license; preserved in LICENSE |

| Full source parameters | 3,973,556,832 (includes embeddings and source modalities) |

| Nile Academy role | Official artifact mirror or explicitly recorded format conversion; no additional training |

Original publisher cards and available notices are preserved in provenance/. The original model licence governs the weights; this repository grants no rights to the Wekala SDK.

Files and quantization

Q8_0 is a higher-precision BF16-derived option, not yet quality-qualified. Official NVIDIA Q4_K_M reduces IFEval-Instruction from 88.0% to 83.9% (4.1 points); do not treat Q4 as meeting a 2-point loss margin.

| File | Quantization | Size (GB) | Origin |

| --- | --- | ---: | --- |

| NVIDIA-Nemotron3-Nano-4B-Q4_K_M.gguf | Q4_K_M | 2.837 | official publisher export |

| NVIDIA-Nemotron-3-Nano-4B-Q8_0-llamacpp-4413a19.gguf | Q8_0 | 4.234 | Wekala conversion from official BF16 |

Exact file SHA-256 values, upstream paths/revisions and conversion receipts are recorded in model-metadata.json.

Published benchmarks

Publisher-reported source-model scores follow. They are not Wekala measurements of these quantized files. Harness, precision, reasoning settings and task versions differ; do not treat them as a normalized cross-model ranking.

| Benchmark | Score (%) | Mode / settings |

| --- | ---: | --- |

| BFCL-V3 | 61.1 | non-thinking; Official reasoning-on/off evaluation tables; publisher prompts and settings, not a Wekala quantization result. |

| IFEval-Prompt | 82.8 | non-thinking; Official reasoning-on/off evaluation tables; publisher prompts and settings, not a Wekala quantization result. |

| IFEval-Prompt | 87.9 | thinking; Official reasoning-on/off evaluation tables; publisher prompts and settings, not a Wekala quantization result. |

| AIME25 | 78.5 | thinking; Official reasoning-on/off evaluation tables; publisher prompts and settings, not a Wekala quantization result. |

| MATH500 | 95.4 | thinking; Official reasoning-on/off evaluation tables; publisher prompts and settings, not a Wekala quantization result. |

| GPQA | 53.2 | thinking; Official reasoning-on/off evaluation tables; publisher prompts and settings, not a Wekala quantization result. |

Exact source card.

Qualification and use

BF16 and Q8 passed a Windows CPU raw-text load/numerical screen. Chat/tool/template fidelity, sustained GPU fit and mobile/browser qualification remain pending.

Wekala broad quantization-quality qualification: not qualified. No general “no significant quality loss” claim is made. Official QAT or publisher comparisons are attributed separately. Before recommendation, use paired reference/variant evaluation across instruction, knowledge, math, multilingual/Arabic and tool tasks under the registered Wekala campaign.

Device fit is separate: weight size excludes context state, scratch buffers and driver headroom. CPU and CUDA are execution backends for the same weight file, not separate models. Mobile/browser and sustained 8GB-VRAM operation require their own measured profiles.

Models can produce incorrect or unsafe outputs. Tool calls are proposals subject to the consuming application’s permissions and controller admission.