Instructions to use abacusai/Smaug-Nemotron-3.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use abacusai/Smaug-Nemotron-3.5 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="abacusai/Smaug-Nemotron-3.5", trust_remote_code=True)
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForMultimodalLM
model = AutoModelForMultimodalLM.from_pretrained("abacusai/Smaug-Nemotron-3.5", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use abacusai/Smaug-Nemotron-3.5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "abacusai/Smaug-Nemotron-3.5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "abacusai/Smaug-Nemotron-3.5",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/abacusai/Smaug-Nemotron-3.5

SGLang

How to use abacusai/Smaug-Nemotron-3.5 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "abacusai/Smaug-Nemotron-3.5" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "abacusai/Smaug-Nemotron-3.5",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "abacusai/Smaug-Nemotron-3.5" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "abacusai/Smaug-Nemotron-3.5",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use abacusai/Smaug-Nemotron-3.5 with Docker Model Runner:
```
docker model run hf.co/abacusai/Smaug-Nemotron-3.5
```

1. Model Introduction

Smaug-Nemotron-3.5 is an agentic fine-tune of NVIDIA Nemotron 3.5 Super VL 120B-A12B, a 120B-parameter (12B active) hybrid Mamba-2 / MoE / Attention vision-language model, fine-tuned by Abacus.AI. It improves on the base on agentic coding (+8.4 on Terminal-Bench 2.1, +2.7 on DeepSWE, +2.3 and +0.7 on the LiveBench 2.0 Agentic and Coding boards, +1.2 on SWE-bench Verified and +1.2 on SWE-bench Multilingual) and holds reasoning, coding, instruction-following, long-context and vision scores at parity with the base (GPQA Diamond, LiveCodeBench v6, SciCode, IFBench, AA-LCR and V*).

The fine-tune adapts behaviour only. Every architectural parameter is unchanged from the base: same 120B hybrid MoE, same vision encoder, same tokenizer, same chat template, same reasoning on/off switch. Any inference stack that serves Nemotron 3.5 Super VL BF16 serves this model as a drop-in replacement.

This card describes the training approach and the evaluation results. Training data consists of filtered multi-turn, tool-using coding trajectories.

2. Model Summary


Base Model	`nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16`
Total Parameters	120B (12B active)
Architecture	Mamba-2 + MoE + Attention hybrid with a C-RADIO vision encoder and an MTP head (unchanged)
Inputs / Outputs	Text, images and video / text (as the base)
Precision	BF16
Context Length	Up to 1M tokens (as the base)
Reasoning Mode	On by default; configurable via chat template (`enable_thinking=True/False`)
Recommended Sampling	Temperature 1.0, Top_P 0.95 (vision: temperature 0.6, as the base)
Adaptation	Supervised fine-tuning on agentic trajectories
License	OpenMDW License Agreement, version 1.1 (inherited)

3. Evaluation

Smaug-Agentic-Nemotron vs its base

Higher is better. Base and Nemotron 3 Ultra scores from the Nemotron 3.5 Super VL model card and livebench.ai.

	Smaug-Nemotron-3.5	Nemotron 3.5 Super VL	Nemotron 3 Ultra
Agentic Coding
SWE-bench Verified	72.3	71.1	73.9
SWE-bench Multilingual	68.9	67.7	68.8
Terminal-Bench 2.1	69.1	60.7	54.8
DeepSWE [offline]	27.4	24.7	3.0
NL2RepoBench	32.2	30.2^†	N/A
LiveBench 2.0 (Agentic)	18.1	15.8	11.2
LiveBench 2.0 (Coding)	66.2	65.5	43.6
Reasoning
GPQA Diamond	90.7	89.5	87.0
Coding
LiveCodeBench v6	88.7	88.2	89.2
SciCode (subtask)	47.7	47.1	42.0
Instruction Following
IFBench	72.0	70.9	82.9
Long Context
AA-LCR v1.1	68.8	68.6	75.2
Vision
V*	85.2	85.6	N/A

Bold = best score in the row. Smaug-Agentic-Nemotron scores are our runs (protocols in Notes below). Base and Nemotron 3 Ultra scores are as reported on the Nemotron 3.5 Super VL model card; we did not re-run them, except NL2RepoBench (†), which neither card reports: that base score is our own run under the identical stack, scaffold and sampling. Base and Nemotron 3 Ultra LiveBench 2.0 rows are the official LiveBench 2.0 leaderboard entries. N/A = not applicable, as on the NVIDIA card.

LiveBench 2.0 category profile

Scores 0–100 on LiveBench 2.0; overall = mean of the seven boards. Base scores are the published leaderboard entry.

Notes

All results were produced with vLLM serving the BF16 weights (FP8 KV cache, no MTP speculative decoding) on NVIDIA B300 GPUs, temperature = 1.0, top_p = 0.95 (AA-LCR: top_p 1.0, as in NVIDIA's recipe; V*: temperature 0.6, the base's vision setting), thinking enabled, following the NVIDIA Nemotron 3.5 Super reproducibility recipes wherever one exists.

SWE-bench Verified: NVIDIA NeMo Gym recipe (OpenCode agent), average of 3 runs over all 500 tasks.
SWE-bench Multilingual: NVIDIA NeMo Gym recipe (OpenCode agent), average of 6 runs over all 300 tasks, scored with NVIDIA's grader as is.
Terminal-Bench 2.1: NVIDIA NeMo Gym recipe with the Terminus 2 agent, average of 4 runs over all 89 tasks, with past reasoning kept in the conversation history (see Section 7).
DeepSWE [offline]: NVIDIA NeMo Gym DeepSWE environment with the OpenCode agent, the harness behind the base card's "DeepSWE [offline]" row; pass@1 over all 113 tasks, single run.
NL2RepoBench: the benchmark's official OpenHands 0.56 scaffold (NVIDIA publishes no recipe), mean fraction of hidden pytest tests passed over all 104 tasks, up to 500 agent steps with 196k input and 64k output tokens per step, single run; the base was run by us under the identical stack, and the difference is within run-to-run variance.
LiveCodeBench v6: official recipe, 454 problems, pass@1, average of 4 runs.
SciCode: official recipe, subtask accuracy over 288 sub-steps (65 problems), average of 3 runs.
AA-LCR v1.1: official recipe, 100 questions, average of 5 runs.
V*: NVIDIA publishes no recipe, so we used our own harness following the protocol in NVIDIA's technical report: static multiple choice without a visual-search tool, full-resolution images, answers matched by letter with a GPT-3.5-Turbo fallback extractor; 191 questions, average of 4 runs.
GPQA Diamond: official recipe, 198 questions × 8 samples, single run.
IFBench: official recipe, 300 prompts × 8 samples, strict reward (NVIDIA's metric), single run.
LiveBench 2.0: overall is the mean of all seven boards. Both models accept image input, so the screenshot-driven Browser board is scored for both.

4. Training Approach

Smaug-Nemotron-3.5 was fine-tuned from the base model to improve agentic coding, tool usage, and long-horizon multi-turn work, using curated multi-turn, tool-using trajectories with the model's reasoning kept in the conversation history. Throughout training we deliberately preserved the base model's original thinking behaviour: training steers the model's actions while keeping its reasoning close to the base, so that the general capabilities of the model are not lost. The reasoning, coding and long-context results above, all at parity with the base, reflect this. Only the language model was adapted; the vision encoder, the vision-language connector and the MTP head are identical to the base. No architectural changes were made.

5. General Capabilities

Reasoning, coding, instruction-following, long-context and vision benchmarks (GPQA Diamond, LiveCodeBench v6, SciCode, IFBench, AA-LCR, V*) are at parity with the base: the gains are in agentic coding.

6. Deployment

Because the architecture is unchanged, Smaug-Nemotron-3.5 runs anywhere the Nemotron 3.5 Super VL BF16 checkpoint runs. Use the base model's deployment recipes with MODEL=abacusai/smaug-agentic-nemotron.

4× H100 with vLLM (vLLM version: vllm/vllm-openai:v0.32.0), up to 1M context:

export MODEL=abacusai/Smaug-Nemotron-3.5
vllm serve $MODEL \
  --served-model-name Smaug-Nemotron-3.5 \
  --tensor-parallel-size 4 \
  --trust-remote-code \
  --kv-cache-dtype fp8 \
  --async-scheduling \
  --allowed-local-media-path=/ \
  --max-num-seqs 32 \
  --enable-mamba-shared-prefix-checkpoint \
  --limit-mm-per-prompt '{"video": 1, "image": 1}' \
  --video-pruning-rate 0.5 \
  --media-io-kwargs '{"video": {"fps": 2, "num_frames": 256}}' \
  --enable-auto-tool-choice \
  --tool-call-parser qwen3_coder \
  --reasoning-parser nemotron_v3 \
  --speculative_config.method mtp \
  --speculative_config.num_speculative_tokens 5 \
  --default-chat-template-kwargs '{"truncate_history_thinking": false}'

Our evaluations ran on vLLM with --kv-cache-dtype fp8 and without MTP.

7. Model Usage

Sampling behaviour is inherited from the base: temperature 1.0, top_p 0.95, the settings used for every number above (AA-LCR: top_p 1.0, as in NVIDIA's recipe). For image and video input, use the base's vision settings, temperature 0.6, top_p 0.95, as for V* above. For reasoning on/off, image, video, streaming and tool-calling examples, see the base model's API client section; all of them apply unchanged with model = "smaug-agentic-nemotron" (the served model name above).

Coding Agent Framework

The model is trained for multi-turn tool use and works with agent frameworks that speak the OpenAI chat-completions contract.

For multi-turn conversations and tool calls, pass the complete assistant message back to messages, including the reasoning field and tool_calls, not just content. The chat template drops past reasoning by default; serve with truncate_history_thinking: false (as above) to keep it. The agentic coding numbers above were produced with thinking history kept in context.

8. License

Smaug-Nemotron-3.5 is a derivative of NVIDIA Nemotron 3.5 Super VL 120B-A12B and is released under the OpenMDW License Agreement, version 1.1, inherited from the base model. For the base model's bias, explainability, privacy and safety documentation, see the base model card.

This model is not affiliated with or endorsed by NVIDIA.

9. Citation

@misc{abacusai2026smaugnemotron35,
  title  = {Smaug-Nemotron=3.5},
  author = {Abacus.AI},
  year   = {2026},
  note   = {Agentic supervised fine-tune of nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16},
  url    = {https://huggingface.co/abacusai/Smaug-Nemotron-3.5}
}

10. Contact Us

If you have any questions, please reach out at Abacus.AI.

Downloads last month: 13

Safetensors

Model size

124B params

Tensor type

BF16

F32

I64

Model tree for abacusai/Smaug-Nemotron-3.5

Base model

nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16

Finetuned

(10)

this model