Nemotron H 8B Reasoning 128K — Hardware Requirements & GPU Compatibility
ChatReasoning
Nemotron H 8B Reasoning 128K is a 8.1B-parameter open language model from NVIDIA in the Nemotron family. At BF16 it needs about 17.82 GB of VRAM — see which GPUs and Macs can run it below.
Runs well on a 24 GB GPU
Runs on 24 GB (BF16 · ~37 tok/s · 32K)Macs from 24 GB (BF16 · ~12 tok/s)
Other
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Nemotron H 8B Reasoning 128K
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve nvidia/Nemotron-H-8B-Reasoning-128K --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Other ways
each opens step-by-stepRun in cloud
Fits on RTX PRO 4500 (32 GB) (11 GB headroom) · BF16
- Generation speed
- ~33 tok/s
- generation speed
- Cost per 1M output tokens
- $2.89
- per 1M output tokens
How Much VRAM Does Nemotron H 8B Reasoning 128K Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 17.8 GB | 23.3 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 32K context · ~37 tok/s |
Selected BF16
Brain floating point 1620.4GBat 16K context
- Weights
- 17.2 GB
- KV cache
- 3.0 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 3.6 GB free · ~37 tok/s
≥50 tok/s needs ≥1.37 TB/s · RTX 5090 ~65
Which Hardware Can Run Nemotron H 8B Reasoning 128K?
BF16 · 17.8 GBNemotron H 8B Reasoning 128K (BF16) requires 17.8 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 24+ GB is recommended. 8 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 122 devices with unified memory can run Nemotron H 8B Reasoning 128K, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Mini M5 Pro (24 GB).
20 GB
tight · up to 8K ctx
1 GPU
RX 7900 XT~27Simulate output on RX 7900 XT32–40 GB
fits · 11.6 GB free · up to 32K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~65Simulate output on RTX 5090M5 Max36 GB~18Simulate output on Mac Studio M5 Max (36 GB)M532 GB~6Simulate output on MacBook Air 13" M5 (32 GB)Orin~8Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~5Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at BF16
Alternatives to Nemotron H 8B Reasoning 128K
Nemotron family · 42 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| ALoDLM 8BAmazon | — | 7.6 GB | ~119 | same size |
| Llm Jp 4.1 8B Thinkingllm-jp | — | 7.6 GB | ~115 | same size |
| Ling 3.0 TinyInclusion AI | — | 5.5 GB | ~364 | same size |
| LFM2.5 8B A1BLiquid AI | — | 5.6 GB | ~335 | same size |
| BitCPM CANN 8BOpenBMB | — | 5.6 GB | ~127 | same size |
| Gemma 4 E4BGoogle | — | 5.6 GB | ~123 | same size |
Specifications
- Publisher
- NVIDIA
- Family
- Nemotron
- Parameters
- 8.1B
- Release Date
- 2025-06-05
- License
- Other
Frequently Asked Questions
How much VRAM does Nemotron H 8B Reasoning 128K need?
Nemotron H 8B Reasoning 128K requires 17.8 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 8.1B × 16 bits ÷ 8 = 16.2 GB
KV Cache + Overhead ≈ 1.6 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
VRAM usage by quantization
Can I run Nemotron H 8B Reasoning 128K on a Mac?
Yes — Mac Mini M5 Pro (24 GB) and 106 other Macs can run Nemotron H 8B Reasoning 128K. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 17.8 GB of usable unified memory (RAM minus macOS overhead).
Can I run Nemotron H 8B Reasoning 128K locally?
Yes — Nemotron H 8B Reasoning 128K can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Nemotron H 8B Reasoning 128K?
At BF16, Nemotron H 8B Reasoning 128K can reach ~269 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~37 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 17.8 × 0.65 = ~292 tok/s
Estimated speed at BF16 (17.8 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Nemotron H 8B Reasoning 128K?
At BF16, the download is about 16.20 GB.
Which GPUs can run Nemotron H 8B Reasoning 128K?
8 consumer GPUs can run Nemotron H 8B Reasoning 128K at BF16. Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX. 1 GPU has plenty of headroom for comfortable inference.
Which devices can run Nemotron H 8B Reasoning 128K?
122 devices with unified memory can run Nemotron H 8B Reasoning 128K at BF16 (17.8 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.