NVIDIA Nemotron 3.5 Lightning 30B A3B Base BF16 — Hardware Requirements & GPU Compatibility
Chat
NVIDIA Nemotron 3.5 Lightning 30B A3B Base BF16 is a 31.6B-parameter open language model from NVIDIA in the Nemotron family. It supports a context window of up to 262,144 tokens. At Q4_K_M it needs about 19.32 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 16 GB (Q3_K_M · 32K)Best on 24 GB (Q4_K_M · ~197 tok/s · 256K)Macs from 18 GB (Q2_K · ~49 tok/s)
Other
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run NVIDIA Nemotron 3.5 Lightning 30B A3B Base BF16
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
ollama run hf.co/mradermacher/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Base-BF16-i1-GGUFQ4_K_M fits fully on the RTX 4090 · 4.7 GB free · 16K context
Download: NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Base-BF16.i1-Q4_K_M.gguf25.43 GBmradermacher
Ways to runOther ways
each opens step-by-stepRun in cloud
Your own private copy · Q4_K_M · 24 GB GPU
- The easiest way to try this model
- Running in a few minutes, easy setup
- Chat right here or connect any app
$5+ bonus for new users
Runs on RTX A5000 (24 GB) (4 GB headroom) · Q4_K_M
- Generation speed
- ~174 tok/s
- generation speed
- Cost per 1M output tokens
- $0.26
- per 1M output tokens
How Much VRAM Does NVIDIA Nemotron 3.5 Lightning 30B A3B Base BF16 Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 13.8 GB | 13.9 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 256K context · ~226 tok/s | |
| 15.8 GB | 15.9 GB | 3-bit medium — 3-bit medium quantization | Fits: 256K context · ~215 tok/s | |
| 19.3 GB | 19.4 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 256K context · ~197 tok/s | |
| 22.9 GB | 23 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 128K context · ~183 tok/s | |
| 26.4 GB | 26.5 GB | 6-bit, very good — 6-bit quantization, very good quality | Does not fit: needs 26.4 GB | |
| 31.9 GB | 32 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Does not fit: needs 32 GB | |
| 63.5 GB | 63.6 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Does not fit: needs 63.5 GB |
Selected Q4_K_M
4-bit medium quantization19.3GBat 16K context
- Weights
- 19.0 GB
- KV cache
- 0.1 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 4.7 GB free · ~197 tok/s
≥50 tok/s needs ≥130 GB/s · RTX 5090 ~244, RTX 3090 Ti ~197
Which Hardware Can Run NVIDIA Nemotron 3.5 Lightning 30B A3B Base BF16?
Q4_K_M · 19.3 GBNVIDIA Nemotron 3.5 Lightning 30B A3B Base BF16 (Q4_K_M) requires 19.3 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 26+ GB is recommended. Using the full 262K context window can add up to 1.2 GB, bringing total usage to 20.5 GB. 8 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 122 devices with unified memory can run NVIDIA Nemotron 3.5 Lightning 30B A3B Base BF16, including NVIDIA DGX Spark, NVIDIA Jetson AGX Thor Developer Kit, Mac Studio M1 Max (32 GB).
20 GB
fits · 0.7 GB free · up to 128K ctx
1 GPU
RX 7900 XT~75Simulate output on RX 7900 XT32–40 GB
fits · 12.7 GB free · up to 256K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~244Simulate output on RTX 5090M5 Max36 GB~67Simulate output on Mac Studio M5 Max (36 GB)M532 GB~42Simulate output on MacBook Air 13" M5 (32 GB)Orin~73Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~46Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to NVIDIA Nemotron 3.5 Lightning 30B A3B Base BF16
Nemotron family · 45 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Nanbeige4.3 33BNanbeige | — | 23.7 GB | ~32 | 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 |
| Llm Jp 4.1 33B Thinkingllm-jp | — | 22.5 GB | ~35 | same size |
| Agnes 3.0 FlashAgnes-AI | — | 22.1 GB | ~35 | same size |
Specifications
- Publisher
- NVIDIA
- Family
- Nemotron
- Parameters
- 31.6B
- Active parameters
- 2.4B per token
- Architecture
- NemotronHForCausalLM
- Context Length
- 262,144 tokens
- Vocabulary Size
- 131,072
- Release Date
- 2026-08-05
- License
- Other
Frequently Asked Questions
How much VRAM does NVIDIA Nemotron 3.5 Lightning 30B A3B Base BF16 need?
NVIDIA Nemotron 3.5 Lightning 30B A3B Base BF16 requires 19.3 GB of VRAM at Q4_K_M, or 63.5 GB at BF16. Full 262K context adds up to 1.2 GB (20.5 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 31.6B × 4.8 bits ÷ 8 = 18.9 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.
KV Cache + Overhead ≈ 1.6 GB (at full 262K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 4090 run NVIDIA Nemotron 3.5 Lightning 30B A3B Base BF16?
Yes, at Q5_K_M (22.9 GB) or lower. Higher quantizations like Q6_K (26.4 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
What's the best quantization for NVIDIA Nemotron 3.5 Lightning 30B A3B Base BF16?
For NVIDIA Nemotron 3.5 Lightning 30B A3B Base BF16, Q4_K_M (19.3 GB) offers the best balance of quality and VRAM usage. Q5_K_M (22.9 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 13.8 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run NVIDIA Nemotron 3.5 Lightning 30B A3B Base BF16 on a Mac?
Yes — MacBook Pro 14" M3 Pro (18 GB) and 108 other Macs can run NVIDIA Nemotron 3.5 Lightning 30B A3B Base BF16, the smallest at Q2_K. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 19.3 GB of usable unified memory (RAM minus macOS overhead), from Mac Mini M5 Pro (24 GB).
Can I run NVIDIA Nemotron 3.5 Lightning 30B A3B Base BF16 locally?
Yes — NVIDIA Nemotron 3.5 Lightning 30B A3B Base BF16 can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is NVIDIA Nemotron 3.5 Lightning 30B A3B Base BF16?
At Q4_K_M, NVIDIA Nemotron 3.5 Lightning 30B A3B Base BF16 can reach ~93 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~197 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 → 1.4 GB active ÷ (8000 × 0.65) = 0.278 ms, plus 52 layers × 0.055 ms = 2.860 ms, so 1000 ÷ 3.138 ms = ~319 tok/s
Estimated speed at Q4_K_M (19.3 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of NVIDIA Nemotron 3.5 Lightning 30B A3B Base BF16?
At Q4_K_M, the download is about 18.95 GB. The full-precision BF16 version is 63.16 GB. The smallest option (Q2_K) is 13.42 GB.
Which GPUs can run NVIDIA Nemotron 3.5 Lightning 30B A3B Base BF16?
8 consumer GPUs can run NVIDIA Nemotron 3.5 Lightning 30B A3B Base BF16 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 NVIDIA Nemotron 3.5 Lightning 30B A3B Base BF16?
122 devices with unified memory can run NVIDIA Nemotron 3.5 Lightning 30B A3B Base BF16 at Q4_K_M (19.3 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.