Back to models
Intelligence Index
Reasoning setting
9.0
Estimated · Artificial Analysis v4.3.2- Context window
- 128K tok
Performance profile
ReasoningArchived source
74.8%
GPQA DiamondCapabilities
Context window
Modalities
Measured setting
Reasoning trade-offs
Source (opens in a new tab)ReasoningEstimated
- Intelligence Index
- 9.0
Pricing & access
No API offering listed in our tracked sources.
Run locally
GGUF
Context
Estimated memory
~32.5 GiB
RAM + VRAM
Estimate assumptions
One text chat at the selected context, with a 16-bit cache and app allowance. Operating system and image processing are extra; optimized caches can use less.
48 GiB RAMwithout GPU offload
Memory budgetOne text chat
- Weights
- 28.1 GiB
- Context cache
- 1.5 GiB16-bit cache
- App allowance
- 2.8 GiB
- Download
- 30.2 GB
- Disk space
- ~39 GB
Get GGUF (opens in a new tab)
Set up in Ollama · Q4_K_M · 8K context
Save the following as Modelfile. The context matches the estimate above.
FROM hf.co/bartowski/nvidia_Llama-3_3-Nemotron-Super-49B-v1_5-GGUF:Q4_K_M PARAMETER num_ctx 8192
Then run these commands in your terminal:
ollama create llmcurrent-local -f Modelfile ollama run llmcurrent-local
Ollama import instructions (opens in a new tab) · For LM Studio or Jan, open the app’s model search, enter bartowski/nvidia_Llama-3_3-Nemotron-Super-49B-v1_5-GGUF, choose Q4_K_M, and set context to 8,192 tokens in the app’s model settings. Software links above open each app’s setup guide.
Benchmarks
Full leaderboardSource (opens in a new tab)7.3%
Humanity’s Last Exam
Frontier reasoning- 1Claude Opus 5.5Max61.4%
- 2Claude Fable 5.1Max59.1%
- 3Gemini 4 ArgonHigh57.1%
- 4Claude Sonnet 5.5Max55.0%
- 5GPT-6 AstraMax54.7%
- 6Muse Wonder FullMax53.6%
- 7GPT-6.1 SolMax52.9%
- 8Muse WonderMax50.1%
- 9MiMo-V2.6-ProReasoning49.4%
- 10Muse Spark 1.3Max48.7%
Peers use their best measured result on this benchmark.