Back to Explore
NVIDIA: Llama 3.3 Nemotron Super 49B V1.5
NVIDIA·Released 2025-10-10
Open Source49B131K ctxother
About
Llama-3.3-Nemotron-Super-49B-v1.5 is a 49B-parameter, English-centric reasoning/chat model derived from Meta’s Llama-3.3-70B-Instruct with a 128K context. It’s post-trained for agentic workflows (RAG, tool calling) via SFT across math, code, science, and...
Related Models
Llama Nemotron Super 49B v1.5 (Reasoning)2025-07-25Llama Nemotron Super 49B v1.5 (Non-reasoning)2025-07-25Llama 3.1 Nemotron Nano VL 8B V12025-06-03Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)2025-05-20NVIDIA: Llama 3.1 Nemotron Ultra 253B v12025-04-08Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)2025-04-07Llama 3.3 Nemotron Super 49B v1 (Reasoning)2025-03-18Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)2025-03-18
Pricing
Input
$0.40
per 1M tokens
Output
$0.40
per 1M tokens
Blended
$0.40
per 1M tokens
Cheaper than 55% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.40
Monthly
$12.00
vs. Similar Models
Meta: Llama 3.1 70B Instruct
$0.400%
TheDrummer: UnslopNemo 12B
$0.400%
Qwen3 4B (Reasoning)
$0.40-0%
Qwen3 1.7B (Reasoning)
$0.40-0%
Performance
Context Window
131K
tokens
Larger than 27% of models
Max Output
16K
tokens
13% of context
Context Window Comparison
DeepSeek: DeepSeek V3.2
131KSame
OpenAI: gpt-oss-120b
131KSame
MoonshotAI: Kimi K2 0711
131KSame
Open Source
other49BGGUF / GPTQ / AWQ
Downloads
821.3K
Likes
233
VRAM (FP16)
48-80 GB
GPU
A100 80GB