cyankiwi / text-generation updated 4 months ago

NVIDIA-Nemotron-3-Super-120B-A12B-AWQ-4bit

Name: NVIDIA-Nemotron-3-Super-120B-A12B-AWQ-4bit
Author: cyankiwi

:---:--- Total Parameters 120B (12B active) Architecture LatentMoE - Mamba-2 + MoE + Attention hybrid with Multi-Token Prediction (MTP) Context Length Up to 1M tokens Minimum GPU Requirement 8× H100-80GB Supported Languages English, French, German, Italian, Japanese, Spanish, Chinese Best For Agentic workflows, long-context reasoning, high-volume workloads (e.g. IT ticket automation), tool use, RAG Reasoning Mode Con...

Params

127.2 B

Context

262,144

Downloads 30d

168 K

Likes

Licence: other Not gated SAFETENSORS 7 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days

190 K168 K

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	i32	80.7 GB	108.3 GB	❌ Won’t fit
model.safetensors (bf16, full)	bf16 + 256K ctx	80.7 GB	699.9 GB	❌ Won’t fit

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub

~ · curl · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/nvidia-nemotron-3-super-120b-a12b-awq-4bit
{
  "hf_id": "cyankiwi/NVIDIA-Nemotron-3-Super-120B-A12B-AWQ-4bit",
  "params_b": 127.23,
  "context_length": 262144,
  "license": { "id": "other", "commercial": "unknown" },
  "downloads_30d": 167639,
  "vram_estimates": [
    { "quant": "i32", "gb": 108.3 }
  ],
  "updated_at": "2026-07-28T18:08:44Z"
}

est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture: NemotronHForCausalLM
Parameters: 127.2 B
Tensor type: I32
Context length: 262,144
Vocabulary: 131,072
Licence: other
First seen on the Hub: 2026-03-16
Base model: NVIDIA-Nemotron-3-Super-120B-A12B-BF16
Training datasets: nvidia/nemotron-post-training-v3, nvidia/nemotron-pre-training-datasets
Added to our catalog: 2026-07-28

Family

Base model and the most-downloaded derivatives in the catalog.

Base NVIDIA-Nemotron-3-Super-120B-A12B-BF16 nvidia 899 K

Compare with

Qwen3-32B 8.3 M dolphin-2.9.1-yi-1.5-34b 4.6 M gpt-oss-120b 4.2 M NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 2.8 M DeepSeek-V4-Flash 2.7 M Qwen3-Coder-Next-FP8 2.2 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB