FitMyLLM
NVIDIA/Dense

NVIDIANemotron-H 47B

Nemotron-H 47B — NVIDIA's hybrid model pushing STEM benchmarks.

chatcodingreasoningmathThinkingDistilled
47B
Parameters
125K
Context length
7
Benchmarks
14
Quantizations
30K
HF downloads
Architecture
Dense
Released
2025-06-06
Layers
98
KV Heads
8
Head Dim
128
Family
nemotron

Quantization Options

Context length:
QuantBitsVRAM @ 16KQuality
IQ3_XXS3.25
19.8 GB
19.6 + 0.2 KV
low
IQ3_XS3.5
21.3 GB
21.1 + 0.2 KV
low
Q3_K_S3.64
22.1 GB
21.9 + 0.2 KV
low
IQ3_M3.76
22.8 GB
22.6 + 0.2 KV
low
Q3_K_M4
24.2 GB
24.0 + 0.2 KV
low
Q3_K_L4.3
26.0 GB
25.8 + 0.2 KV
moderate
IQ4_XS4.46
26.9 GB
26.7 + 0.2 KV
moderate
Q4_K_S4.67
28.2 GB
27.9 + 0.2 KV
moderate
Q4_K_M4.89
29.5 GB
29.2 + 0.2 KV
good
Q5_K_S5.57
33.4 GB
33.2 + 0.2 KV
good
Q5_K_M5.7
34.2 GB
34.0 + 0.2 KV
good
Q6_K6.56
39.3 GB
39.0 + 0.2 KV
excellent
Q8_08.5
50.7 GB
50.4 + 0.2 KV
lossless
FP1616
94.7 GB
94.5 + 0.2 KV
lossless

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

Deploying for a team or in production? Size GPUs, cost & scaling in Enterprise →
Ready to run this?Rent by the hour

Rent a GPU and run Nemotron-H 47B now

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

Community Ratings

Loading ratings...

Benchmarks (7)

Run this model

Easiest way to get started·Beginners
Docs ↗
curl -fsSL https://ollama.com/install.sh | sh
$# Nemotron-H 47B is not in Ollama's library, and we know no GGUF build of it

Search Hugging Face for a GGUF of it (https://huggingface.co/models?sort=trending&search=Nemotron-H-47B-Reasoning-128K+GGUF), or use the vLLM tab with the original weights.

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

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

Apple M1 Max (32GB)
32 GB VRAM • 400 GB/s
APPLE
$1499
Apple M2 Max (32GB)
32 GB VRAM • 400 GB/s
APPLE
$1799
NVIDIA V100 SXM2 32GB
32 GB VRAM • 900 GB/s
NVIDIA
$3500
Apple M2 Pro (32GB)
32 GB VRAM • 200 GB/s
APPLE
$1499
Apple M4 (32GB)
32 GB VRAM • 120 GB/s
APPLE
$1199
NVIDIA Tesla V100 DGXS 32 GB
32 GB VRAM • 897 GB/s
NVIDIA
NVIDIA Tesla V100 PCIe 32 GB
32 GB VRAM • 897 GB/s
NVIDIA
NVIDIA Tesla V100 SXM2 32 GB
32 GB VRAM • 898 GB/s
NVIDIA
NVIDIA Tesla V100 SXM3 32 GB
32 GB VRAM • 981 GB/s
NVIDIA
AMD Radeon Instinct MI60
32 GB VRAM • 1020 GB/s
AMD
NVIDIA Tesla V100S PCIe 32 GB
32 GB VRAM • 1130 GB/s
NVIDIA
AMD Radeon Instinct MI100
32 GB VRAM • 1230 GB/s
AMD
$5000
NVIDIA Tesla PG500-216
32 GB VRAM • 1130 GB/s
NVIDIA
NVIDIA Tesla PG503-216
32 GB VRAM • 1130 GB/s
NVIDIA

Find the best GPU for Nemotron-H 47B

Build Hardware for Nemotron-H 47B

Nemotron-H 47B — NVIDIA's hybrid model pushing STEM benchmarks.

Spec sheet

Nemotron-H 47B — 47B Dense.

Specifications
Parameters
47B
Architecture
Dense Transformer
Context Length
125K tokens
Capabilities
chat, coding, reasoning, math
Release Date
2025-06-06
Provider
NVIDIA
Family
nemotron
VRAM requirements
QuantBPWVRAMQuality
IQ3_XXS3.2519.6 GB82%
IQ3_XS3.521.1 GB84%
Q3_K_S3.6421.9 GB85%
IQ3_M3.7622.6 GB86%
Q3_K_M424.0 GB88%
Q3_K_L4.325.8 GB90%
IQ4_XS4.4626.7 GB92%
Q4_K_S4.6727.9 GB93%
Q4_K_M4.8929.2 GB94%
Q5_K_S5.5733.2 GB96%
Q5_K_M5.734.0 GB96%
Q6_K6.5639.0 GB97%
Q8_08.550.4 GB100%
FP161694.5 GB100%
Benchmark scores
MATH96.2
IFEval84.5
GPQA65.7
MBPP91.8
Arena Elo1312
LiveCodeBench50.2
AIME54.2
Compatible GPUs
30 @ Q4_K_M