NVIDIA
NVIDIA
Language model · United States ·Sep 2022

NeMO Megatron GPT 20B

Language Open (Restricted)
20B
Parameters

About NeMO Megatron GPT 20B

NeMO Megatron GPT 20B is an AI model developed by NVIDIA, in the language category, released in 2022, made available as an open-weights model with 20B params.

On this page you'll find NeMO Megatron GPT 20B's full specifications. Review provider pricing and benchmark scores below, or compare NeMO Megatron GPT 20B head-to-head with other language models.

→ More models by NVIDIA → All language models → AI benchmarks leaderboard

Links

Announcement ↗

Run NeMO Megatron GPT 20B locally — what to buy

Share this build ↗

Sized to what NeMO Megatron GPT 20B actually needs (~8k context at Q4), not to the biggest GPU: Good = cheapest that runs it, Better = best value, Best = most headroom. Speed is a hardware estimate; anything past ~120 tok/s is shown as instant.

Good
Intel Arc A770 16GB
Consumer GPU · ~$329
~36 tok/s
Q4 · tight on context · up to 8k ctx
Runs with: ExLlamaV2, KoboldCpp, LM Studio
See full estimate →
Better
NVIDIA GeForce RTX 5070 Ti
Consumer GPU · ~$749
~69.6 tok/s
Q4 · tight on context · up to 8k ctx
Runs with: ExLlamaV2, KoboldCpp, LM Studio
See full estimate →
Best
NVIDIA GeForce RTX 5090
Consumer GPU · ~$1,999
~120 tok/s
Q4 · fits full context · up to 8k ctx
Runs with: ExLlamaV2, KoboldCpp, LM Studio
See full estimate →

Software support

·ExLlamaV2 ·KoboldCpp ·LM Studio ·MLX ·Ollama ·SGLang ·TensorRT-LLM ·llama.cpp ·vLLM ?KTransformers ?text-generation-webui

✓ measured · · compatible · — not supported. Informational only — speed is hardware-based.

Consumer GPU
14.4–120+ tok/s
22 options →
Apple
22–58.6 tok/s
17 options →
Datacenter GPU
59.4–120+ tok/s
13 options →

Community

Would you run NeMO Megatron GPT 20B again?
No votes yet — be the first.
Did it run? — community reports by hardware

No reports yet. Own this model on some hardware? Be the first to confirm it runs.

Discussion

No comments yet. Start the discussion.

More models like NeMO Megatron GPT 20B

AI
DMind-1
 AI
COLLECTIVE-1
 AI
Cogito 1 series
 AI
Euler (Euler大模型)
· 2.5B
 AI
SmolLM-1.7B
· 1.7B
 AI
Llama-3-70B-Synthia-v3.5
· 70B

Frequently asked questions

What is NeMO Megatron GPT 20B? ▶

NeMO Megatron GPT 20B is an AI model developed by NVIDIA, in the language category, released in 2022. It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created NeMO Megatron GPT 20B? ▶

NeMO Megatron GPT 20B was developed by NVIDIA and released in 2022.

Is NeMO Megatron GPT 20B open source or proprietary? ▶

NeMO Megatron GPT 20B ships as an open-weights model: you can download and self-host the weights, though the licence may place some restrictions on use.

How much does NeMO Megatron GPT 20B cost? ▶

Pricing for NeMO Megatron GPT 20B depends on the provider. See the providers table on this page for the latest API rates.

How does NeMO Megatron GPT 20B perform on benchmarks? ▶

Benchmark scores for NeMO Megatron GPT 20B are listed on this page as they are published. You can compare it head-to-head with other models on the GenAIList compare tool.

No videos yet. Know a good one? Add it below.

Know a great video about NeMO Megatron GPT 20B?