An abliterated (uncensored) build of nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4. Refusal behaviour has been removed while the original model's quality and NVIDIA's NVFP4 quantization are preserved exactly as shipped. The checkpoint is a drop-in replacement for the base model and loads unmodified on both vLLM and TensorFold. Developed and measured on a single NVIDIA DGX Spark (GB10).
The modification is a lightweight, quantization-preserving weight edit. The procedure is proprietary and not disclosed.
Nemotron-3.5-Super-VL is a NemotronH hybrid vision-language model: a Mamba-2 / attention / latent mixture-of-experts language backbone (120 B total, ~12 B active parameters), a C-RADIO vision tower, and a multi-token-prediction (MTP) draft head, in NVIDIA ModelOpt mixed-precision NVFP4. See the base model card for the complete specification.
Measured head-to-head on one DGX Spark (GB10), greedy decoding. Quality, speed and refusal numbers are both the original and this model served identically on TensorFold 1.1.2; the faithfulness (KL) numbers are both served on vLLM. Every "original" figure is the unmodified base checkpoint on the same harness.
Quality — unchanged (TensorFold 1.1.2):
| Metric | Original | This model |
|---|---|---|
| 130-task suite — gsm8k50 / json / instruct / tools / agent | 49 / 15 / 8 / 20 / 10 | 49 / 15 / 8 / 20 / 10 |
| Executed code (25) | 25/25 | 25/25 |
| GSM8K-300 (thinking off) | 293/300 | 292/300 |
Faithfulness to the original (vLLM, teacher-forced over 64,319 positions of code / prose / chat / long-context / reasoning documents; KL over the top-20 tokens, so a lower bound):
| KL vs original | top-1 agreement | ΔNLL | |
|---|---|---|---|
| Run-to-run noise floor (original vs itself) | 0.0138 | — | — |
| This model | 0.0157 | 95.74 % | +0.0013 |
The output distribution sits barely past the measurement's own noise floor — to within the harness's resolution, the same model.
Speed — no cost (TensorFold 1.1.2, single stream, built-in MTP drafter):
| Workload | Original | This model | MTP draft tokens / round (this model) |
|---|---|---|---|
| Code decode tok/s | 51.1 | 56.2 | 4.74 |
| Chat decode tok/s | 39.2 | 38.8 | — |
MTP drafter acceptance is identical to the original (4.74 tokens/round on code), so speculative decoding is unaffected.
Refusals (TensorFold 1.1.2):
| Set | Original | This model |
|---|---|---|
| Harmful + jailbreak (204) | 200/204 refused (98.0 %) | 4/204 refused (2.0 %) |
| Benign answered (100) | 69/100 | 99/100 |
Refusals are judged by a keyword rule over the model's final answer — a calibration aid, not a safety evaluation (see Limitations). The "benign answered" row checks that the modification does not make the model refuse ordinary prompts; it answers more of them than the original, not fewer.
The checkpoint is a drop-in replacement for the base model. Recommended sampling is the base model's own.
vLLM
vllm serve <repo> \
--trust-remote-code \
--served-model-name nemotron-3.5-super-vl \
--max-num-batched-tokens 8192 \
--media-io-kwargs '{"video": {"fps": 2, "num_frames": 256}}' \
--video-pruning-rate 0.5 \
--reasoning-parser nemotron_v3 \
--enable-auto-tool-choice --tool-call-parser qwen3_coder
NVIDIA's LiLiCorr speculative-decoding drafter can be attached unchanged.
TensorFold (native CUDA engine, with the built-in MTP drafter)
tensorfold-native serve <path-to-model> \
--name nemotron-3.5-super-vl --vision --context 1048576
Both expose an OpenAI-compatible API. --vision enables image and video input.
Use of this model is governed by the base model's license, the OpenMDW License Agreement, version 1.1. This is a derivative of NVIDIA's Nemotron-3.5-Super-VL and inherits its terms.
Not affiliated with or endorsed by NVIDIA.
model-00088-of-00088.safetensors 3.9 GBmodel-00001-of-00088.safetensors 2.9 GBmodel-00011-of-00088.safetensors 1.6 GBmodel-00013-of-00088.safetensors 1.6 GBmodel-00015-of-00088.safetensors 1.6 GBmodel-00018-of-00088.safetensors 1.6 GBmodel-00020-of-00088.safetensors 1.6 GBmodel-00022-of-00088.safetensors 1.6 GBmodel-00024-of-00088.safetensors 1.6 GBmodel-00027-of-00088.safetensors 1.6 GBmodel-00029-of-00088.safetensors 1.6 GBmodel-00031-of-00088.safetensors 1.6 GBmodel-00033-of-00088.safetensors 1.6 GBmodel-00035-of-00088.safetensors 1.6 GBmodel-00038-of-00088.safetensors 1.6 GBmodel-00040-of-00088.safetensors 1.6 GBmodel-00042-of-00088.safetensors 1.6 GBmodel-00044-of-00088.safetensors 1.6 GBmodel-00046-of-00088.safetensors 1.6 GBmodel-00049-of-00088.safetensors 1.6 GBmodel-00051-of-00088.safetensors 1.6 GBmodel-00053-of-00088.safetensors 1.6 GBmodel-00055-of-00088.safetensors 1.6 GBmodel-00057-of-00088.safetensors 1.6 GBmodel-00060-of-00088.safetensors 1.6 GBmodel-00062-of-00088.safetensors 1.6 GBmodel-00064-of-00088.safetensors 1.6 GBmodel-00066-of-00088.safetensors 1.6 GBmodel-00068-of-00088.safetensors 1.6 GBmodel-00071-of-00088.safetensors 1.6 GBmodel-00073-of-00088.safetensors 1.6 GBmodel-00075-of-00088.safetensors 1.6 GBmodel-00077-of-00088.safetensors 1.6 GBmodel-00080-of-00088.safetensors 1.6 GBmodel-00082-of-00088.safetensors 1.6 GBmodel-00084-of-00088.safetensors 1.6 GBmodel-00086-of-00088.safetensors 1.6 GBmodel-00002-of-00088.safetensors 1.6 GBmodel-00004-of-00088.safetensors 1.6 GBmodel-00006-of-00088.safetensors 1.6 GBmodel-00009-of-00088.safetensors 1.6 GBmodel-00012-of-00088.safetensors 110 MBmodel-00014-of-00088.safetensors 110 MBmodel-00016-of-00088.safetensors 110 MBmodel-00019-of-00088.safetensors 110 MBmodel-00021-of-00088.safetensors 110 MBmodel-00023-of-00088.safetensors 110 MBmodel-00025-of-00088.safetensors 110 MBmodel-00028-of-00088.safetensors 110 MBmodel-00030-of-00088.safetensors 110 MBmodel-00032-of-00088.safetensors 110 MBmodel-00034-of-00088.safetensors 110 MBmodel-00036-of-00088.safetensors 110 MBmodel-00039-of-00088.safetensors 110 MBmodel-00041-of-00088.safetensors 110 MBmodel-00043-of-00088.safetensors 110 MBmodel-00045-of-00088.safetensors 110 MBmodel-00047-of-00088.safetensors 110 MBmodel-00050-of-00088.safetensors 110 MBmodel-00052-of-00088.safetensors 110 MBmodel-00054-of-00088.safetensors 110 MBmodel-00056-of-00088.safetensors 110 MBmodel-00058-of-00088.safetensors 110 MBmodel-00061-of-00088.safetensors 110 MBmodel-00063-of-00088.safetensors 110 MBmodel-00065-of-00088.safetensors 110 MBmodel-00067-of-00088.safetensors 110 MBmodel-00069-of-00088.safetensors 110 MBmodel-00072-of-00088.safetensors 110 MBmodel-00074-of-00088.safetensors 110 MBmodel-00076-of-00088.safetensors 110 MBmodel-00078-of-00088.safetensors 110 MBmodel-00081-of-00088.safetensors 110 MBmodel-00083-of-00088.safetensors 110 MBmodel-00085-of-00088.safetensors 110 MBmodel-00087-of-00088.safetensors 110 MBmodel-00003-of-00088.safetensors 110 MBmodel-00005-of-00088.safetensors 110 MBmodel-00007-of-00088.safetensors 110 MBmodel-00010-of-00088.safetensors 110 MBmodel-00017-of-00088.safetensors 36 MBmodel-00026-of-00088.safetensors 36 MBmodel-00037-of-00088.safetensors 36 MBmodel-00048-of-00088.safetensors 36 MBmodel-00059-of-00088.safetensors 36 MBmodel-00070-of-00088.safetensors 36 MBmodel-00079-of-00088.safetensors 36 MBmodel-00008-of-00088.safetensors 36 MBnvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4