Nemotron H 8B Base 8K — Hardware Requirements & GPU Compatibility
Chat
Nemotron H 8B Base 8K is a 8.1B-parameter open language model from NVIDIA in the Nemotron family. At Q4_K_M it needs about 5.35 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 16K)Best on 24 GB (Q4_K_M · ~123 tok/s · 32K)Macs from 16 GB (Q4_K_M · ~26 tok/s)
Other
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Nemotron H 8B Base 8K
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
vllm serve nvidia/Nemotron-H-8B-Base-8K --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on RTX 3080 Ti (12 GB) (4 GB headroom) · Q4_K_M
- Generation speed
- ~111 tok/s
- generation speed
- Cost per 1M output tokens
- $0.31
- per 1M output tokens
How Much VRAM Does Nemotron H 8B Base 8K Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 3.8 GB | 9.3 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 32K context · ~173 tok/s | |
| 4.3 GB | 9.9 GB | 3-bit medium — 3-bit medium quantization | Fits: 32K context · ~151 tok/s | |
| 5.3 GB | 10.9 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 32K context · ~123 tok/s | |
| 6.3 GB | 11.9 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 32K context · ~103 tok/s | |
| 7.3 GB | 12.9 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 32K context · ~89 tok/s | |
| 8.9 GB | 14.4 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 32K context · ~74 tok/s | |
| 17.8 GB | 23.3 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 32K context · ~37 tok/s |
Selected Q4_K_M
4-bit medium quantization7.9GBat 16K context
- Weights
- 4.7 GB
- KV cache
- 3.0 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 16.1 GB free · ~123 tok/s
≥50 tok/s needs ≥411 GB/s · RTX 5090 ~218, RTX 3090 Ti ~123
Which Hardware Can Run Nemotron H 8B Base 8K?
Q4_K_M · 5.3 GBNemotron H 8B Base 8K (Q4_K_M) requires 5.3 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 7+ GB is recommended. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3070 Ti. 151 devices with unified memory can run Nemotron H 8B Base 8K, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), NVIDIA Jetson Orin Nano 8GB (Super).
≤ 11 GB
≤ 11 GB tier →fits · 0.1 GB free · up to 16K ctx
16 GPUs · 1 device family
RTX 3080~92Simulate output on RTX 3080RTX 2080 Ti~75Simulate output on RTX 2080 TiRTX 3070 Ti~74Simulate output on RTX 3070 TiOrin Nano~12Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)20 GB
fits · 12.1 GB free · up to 32K ctx
1 GPU
RX 7900 XT~90Simulate output on RX 7900 XT32–40 GB
fits · 24.1 GB free · up to 32K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~218Simulate output on RTX 5090M5 Max36 GB~60Simulate output on Mac Studio M5 Max (36 GB)M532 GB~20Simulate output on MacBook Air 13" M5 (32 GB)Orin~25Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~16Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
How good is Nemotron H 8B Base 8K?
llmrun Score blends public benchmark boards into one number; 100 = the average open model.
Not enough data yet for an llmrun Score.
A Score needs results on enough independent boards. How the Composite Score is built
Benchmarks
This is the single board showing results for this model; badges show who ran the test.
- MMLU-Pro
TIGER-LabIndependent
Independent44.0%
#89/146 open
Alternatives to Nemotron H 8B Base 8K
Nemotron family · 45 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
- Architecture
- NemotronHForCausalLM
- Release Date
- 2025-03-19
- License
- Other
Frequently Asked Questions
How much VRAM does Nemotron H 8B Base 8K need?
Nemotron H 8B Base 8K requires 5.3 GB of VRAM at Q4_K_M, or 17.8 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 8.1B × 4.8 bits ÷ 8 = 4.9 GB
KV Cache + Overhead ≈ 0.4 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
What's the best quantization for Nemotron H 8B Base 8K?
For Nemotron H 8B Base 8K, Q4_K_M (5.3 GB) offers the best balance of quality and VRAM usage. Q5_K_M (6.3 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 3.8 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Nemotron H 8B Base 8K on a Mac?
Yes — Mac Mini M2 Pro (16 GB) and 133 other Macs can run Nemotron H 8B Base 8K. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 5.3 GB of usable unified memory (RAM minus macOS overhead).
Can I run Nemotron H 8B Base 8K locally?
Yes — Nemotron H 8B Base 8K can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Nemotron H 8B Base 8K?
At Q4_K_M, Nemotron H 8B Base 8K can reach ~897 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~123 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 ÷ 5.35 × 0.65 = ~972 tok/s
Estimated speed at Q4_K_M (5.3 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 Base 8K?
At Q4_K_M, the download is about 4.86 GB. The full-precision BF16 version is 16.20 GB. The smallest option (Q2_K) is 3.44 GB.
Which GPUs can run Nemotron H 8B Base 8K?
52 consumer GPUs can run Nemotron H 8B Base 8K at Q4_K_M. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT, AMD Radeon RX 7600. 40 GPUs have plenty of headroom for comfortable inference.
Which devices can run Nemotron H 8B Base 8K?
151 devices with unified memory can run Nemotron H 8B Base 8K at Q4_K_M (5.3 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.