FitMyLLM
NVIDIA/Dense

NVIDIANemotron-H 8B

Nemotron-H 8B — hybrid architecture with strong math and reasoning.

chatcodingreasoningmathThinking
8B
Parameters
125K
Context length
6
Benchmarks
6
Quantizations
50K
HF downloads
Architecture
Dense
Released
2025-06-06
Layers
52
KV Heads
8
Head Dim
128
Family
nemotron

Quantization Options

Context length:
QuantBitsVRAM @ 16KQuality
Q4_K_M4.89
5.6 GB
5.4 + 0.2 KV
good
Q5_K_S5.57
6.2 GB
6.1 + 0.2 KV
good
Q5_K_M5.7
6.4 GB
6.2 + 0.2 KV
good
Q6_K6.56
7.2 GB
7.0 + 0.2 KV
excellent
Q8_08.5
9.2 GB
9.0 + 0.2 KV
lossless
FP1616
16.7 GB
16.5 + 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 8B now

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

Community Ratings

Loading ratings...

Benchmarks (6)

Run this model

Easiest way to get started·Beginners
Docs ↗
curl -fsSL https://ollama.com/install.sh | sh
$# Nemotron-H 8B 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-8B-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.

NVIDIA Tesla C2070
6 GB VRAM • 143 GB/s
NVIDIA
NVIDIA Tesla C2075
6 GB VRAM • 150 GB/s
NVIDIA
NVIDIA Tesla C2090
6 GB VRAM • 177 GB/s
NVIDIA
NVIDIA Tesla M2070
6 GB VRAM • 150 GB/s
NVIDIA
NVIDIA Tesla M2070-Q
6 GB VRAM • 150 GB/s
NVIDIA
NVIDIA Tesla M2075
6 GB VRAM • 150 GB/s
NVIDIA
NVIDIA Tesla M2090
6 GB VRAM • 177 GB/s
NVIDIA
NVIDIA Tesla X2070
6 GB VRAM • 177 GB/s
NVIDIA
NVIDIA Tesla X2090
6 GB VRAM • 177 GB/s
NVIDIA
NVIDIA Tesla K20X
6 GB VRAM • 250 GB/s
NVIDIA
NVIDIA Tesla K20Xm
6 GB VRAM • 250 GB/s
NVIDIA

Find the best GPU for Nemotron-H 8B

Build Hardware for Nemotron-H 8B

Nemotron-H 8B — hybrid architecture with strong math and reasoning.

Spec sheet

Nemotron-H 8B — 8B Dense.

Specifications
Parameters
8B
Architecture
Dense Transformer
Context Length
125K tokens
Capabilities
chat, coding, reasoning, math
Release Date
2025-06-06
Provider
NVIDIA
Family
nemotron
VRAM requirements
QuantBPWVRAMQuality
Q4_K_M4.895.4 GB94%
Q5_K_S5.576.1 GB96%
Q5_K_M5.76.2 GB96%
Q6_K6.567.0 GB97%
Q8_08.59.0 GB100%
FP161616.5 GB100%
Benchmark scores
MATH94.0
GPQA55.1
MBPP86.0
Arena Elo1450
LiveCodeBench49.5
AIME51.7
Compatible GPUs
30 @ Q4_K_M