Elbaz NVIDIA Nemotron 3 Nano 30B A3B PRISM — Hardware Requirements & GPU Compatibility
Chat
Elbaz NVIDIA Nemotron 3 Nano 30B A3B PRISM is a 30B-parameter open language model from Ex0bit in the Nemotron family. At Q4_K_M it needs about 19.80 GB of VRAM — see which GPUs and Macs can run it below.
Usable on a 24 GB GPU
Runs on 24 GB (Q4_K_M · ~177 tok/s · 16K)Macs from 24 GB (Q4_K_M · ~53 tok/s)
Other
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Elbaz NVIDIA Nemotron 3 Nano 30B A3B PRISM
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 Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM --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 5090 (32 GB) (8 GB headroom) · Q4_K_M
- Generation speed
- ~230 tok/s
- generation speed
- Cost per 1M output tokens
- $0.60
- per 1M output tokens
How Much VRAM Does Elbaz NVIDIA Nemotron 3 Nano 30B A3B PRISM Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 14.0 GB | 22 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 32K context · ~209 tok/s | |
| 16.1 GB | 24.1 GB | 3-bit medium — 3-bit medium quantization | Fits: 16K context · ~196 tok/s | |
| 17.7 GB | 25.7 GB | 4-bit · i-quant compact — Importance-weighted 4-bit, compact | Fits: 16K context · ~187 tok/s | |
| 19.8 GB | 27.8 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 16K context · ~177 tok/s | |
| 23.5 GB | 31.5 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 2K context · ~161 tok/s | |
| 27.2 GB | 35.2 GB | 6-bit, very good — 6-bit quantization, very good quality | Does not fit: needs 31 GB | |
| 33 GB | 41 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Does not fit: needs 36.7 GB | |
| 66 GB | 74 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Does not fit: needs 69.7 GB |
Selected Q4_K_M
4-bit medium quantization23.5GBat 16K context
- Weights
- 19.0 GB
- KV cache
- 4.3 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 0.5 GB free · ~177 tok/s
≥50 tok/s needs ≥175 GB/s · RTX 5090 ~230, RTX 3090 Ti ~177
Which Hardware Can Run Elbaz NVIDIA Nemotron 3 Nano 30B A3B PRISM?
Q4_K_M · 19.8 GBElbaz NVIDIA Nemotron 3 Nano 30B A3B PRISM (Q4_K_M) requires 19.8 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 26+ 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 Elbaz NVIDIA Nemotron 3 Nano 30B A3B PRISM, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio M1 Max (32 GB).
20 GB
tight · up to 2K ctx
1 GPU
RX 7900 XT~73Simulate output on RX 7900 XT32–40 GB
fits · 8.5 GB free · up to 32K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~230Simulate output on RTX 5090M5 Max36 GB~64Simulate output on Mac Studio M5 Max (36 GB)M532 GB~36Simulate output on MacBook Air 13" M5 (32 GB)Orin~57Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~37Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to Elbaz NVIDIA Nemotron 3 Nano 30B A3B PRISM
Nemotron family · 45 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Qwen3.8 27BAlibaba | 122.0 | 17.9 GB | ~38 | same size |
| Hy Memory 30B A3BTencent | — | 19.1 GB | ~184 | same size |
| Granite Switch 4.1 30BIBM | — | 22.7 GB | ~35 | same size |
| Llm Jp 4.1 32B A3b Thinkingllm-jp | — | 20.1 GB | ~188 | same size |
| Muse Glimmer 30BMeta | — | 19.6 GB | ~36 | same size |
| Hy MT2 30B A3BTencent | — | 19.1 GB | ~170 | same size |
Specifications
- Publisher
- Ex0bit
- Family
- Nemotron
- Parameters
- 30B
- Active parameters
- 3B per token
- Release Date
- 2025-12-18
- License
- Other
Frequently Asked Questions
How much VRAM does Elbaz NVIDIA Nemotron 3 Nano 30B A3B PRISM need?
Elbaz NVIDIA Nemotron 3 Nano 30B A3B PRISM requires 19.8 GB of VRAM at Q4_K_M, or 66 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 30B × 4.8 bits ÷ 8 = 18 GB
KV Cache + Overhead ≈ 1.8 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 NVIDIA GeForce RTX 4090 run Elbaz NVIDIA Nemotron 3 Nano 30B A3B PRISM?
Yes, at Q5_K_M (23.5 GB) or lower. Higher quantizations like Q6_K (27.2 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
What's the best quantization for Elbaz NVIDIA Nemotron 3 Nano 30B A3B PRISM?
For Elbaz NVIDIA Nemotron 3 Nano 30B A3B PRISM, Q4_K_M (19.8 GB) offers the best balance of quality and VRAM usage. Q5_K_M (23.5 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 14.0 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Elbaz NVIDIA Nemotron 3 Nano 30B A3B PRISM on a Mac?
Yes — Mac Mini M5 Pro (24 GB) and 106 other Macs can run Elbaz NVIDIA Nemotron 3 Nano 30B A3B PRISM. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 19.8 GB of usable unified memory (RAM minus macOS overhead).
Can I run Elbaz NVIDIA Nemotron 3 Nano 30B A3B PRISM locally?
Yes — Elbaz NVIDIA Nemotron 3 Nano 30B A3B PRISM can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Elbaz NVIDIA Nemotron 3 Nano 30B A3B PRISM?
At Q4_K_M, Elbaz NVIDIA Nemotron 3 Nano 30B A3B PRISM can reach ~100 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~177 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = 1000 ÷ (active GB ÷ (bandwidth GB/s × efficiency) × 1000 + layers × routing ms)
Mixture-of-Experts: just the active experts get read for each token, along with a fixed routing cost per layer.
Example: NVIDIA B200 → 2.0 GB active ÷ (8000 × 0.65) = 0.38 ms, plus 48 layers × 0.055 ms = 2.64 ms, so 1000 ÷ 3.02 ms = ~331 tok/s
Estimated speed at Q4_K_M (19.8 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Elbaz NVIDIA Nemotron 3 Nano 30B A3B PRISM?
At Q4_K_M, the download is about 18.00 GB. The full-precision BF16 version is 60.00 GB. The smallest option (Q2_K) is 12.75 GB.
Which GPUs can run Elbaz NVIDIA Nemotron 3 Nano 30B A3B PRISM?
8 consumer GPUs can run Elbaz NVIDIA Nemotron 3 Nano 30B A3B PRISM at Q4_K_M. 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 Elbaz NVIDIA Nemotron 3 Nano 30B A3B PRISM?
122 devices with unified memory can run Elbaz NVIDIA Nemotron 3 Nano 30B A3B PRISM at Q4_K_M (19.8 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.