NVIDIA/Dense

Nemotron-4 340B

Name: Nemotron-4 340B
Author: NVIDIA

Nemotron-4 340B — NVIDIA's massive model for research and enterprise.

chatreasoning

340B

Parameters

Context length

Benchmarks

Quantizations

10K

HF downloads

Architecture

Dense

Released

2024-06-14

Layers

KV Heads

Head Dim

128

Family

nemotron

Quantization Options

Quant	Bits	VRAM	Quality
IQ2_XXS	2.38	101.6 GB	low
IQ2_M	2.93	125.0 GB	low
Q2_K	3.16	134.8 GB	low
IQ3_XXS	3.25	138.6 GB	low
IQ3_XS	3.5	149.2 GB	low
Q3_K_S	3.64	155.2 GB	low
IQ3_M	3.76	160.3 GB	low
Q3_K_M	4	170.5 GB	low
Q3_K_L	4.3	183.2 GB	moderate
IQ4_XS	4.46	190.0 GB	moderate
Q4_K_S	4.67	199.0 GB	moderate
Q4_K_M	4.89	208.3 GB	good
Q5_K_S	5.57	237.2 GB	good
Q5_K_M	5.7	242.7 GB	good
Q6_K	6.56	279.3 GB	excellent
Q8_0	8.5	361.7 GB	lossless
FP16	16	680.5 GB	lossless

Select your GPU above to see speed estimates and compatibility for each quantization.

▸ READY TO RUN THIS?RENT BY THE HOUR

RENT A GPU AND RUN NEMOTRON-4 340B NOW

Rent on RunPod →Or Vast.ai →

Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.

Community Ratings

Loading ratings...

Benchmarks (5)

Arena Elo1482

IFEval85.1

HumanEval73.2

MMLU-PRO62.0

MATH41.1

Run this model

▸Easiest way to get started·Beginners

DOCS ↗

curl -fsSL https://ollama.com/install.sh | sh

$ollama run nemotron:340b-q4_K_M

Tag may need adjustment — check ollama.com/library/nemotron for available tags.

▸ SETUP GUIDE

Auto-setup with fitmyllm CLI

Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.

pip install fitmyllmthen run fitmyllmLearn more

Auto-detect GPULive tok/s in chatSpeed benchmarks9 inference engines

HuggingFace GGUF Downloads Build Hardware