Nemotron Cascade 2 30B A3B — Hardware Requirements & GPU Compatibility
ChatReasoning
Nemotron Cascade 2 30B A3B 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.
92.0K downloads
515 likesSpecifications
- Publisher
- NVIDIA
- Family
- Nemotron
- Parameters
- 31.6B
- Architecture
- NemotronHForCausalLM
- Context Length
- 262,144 tokens
- Vocabulary Size
- 131,072
- Release Date
- 2026-03-18
- License
- Other
Get Started
HuggingFace
How Much VRAM Does Nemotron Cascade 2 30B A3B Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 13.8 GB | 22.9 GB | 13.42 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 14.2 GB | 23.3 GB | 13.82 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 15.8 GB | 24.9 GB | 15.39 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 16.2 GB | 25.3 GB | 15.79 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 19.3 GB | 28.4 GB | 18.95 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 22.9 GB | 32.0 GB | 22.50 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 26.4 GB | 35.5 GB | 26.05 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 31.9 GB | 41.0 GB | 31.58 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run Nemotron Cascade 2 30B A3B?
Q4_K_M · 19.3 GBNemotron Cascade 2 30B A3B (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 9.1 GB, bringing total usage to 28.4 GB. 8 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroom
Which Devices Can Run Nemotron Cascade 2 30B A3B?
Q4_K_M · 19.3 GB41 devices with unified memory can run Nemotron Cascade 2 30B A3B, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 Pro (24 GB).
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightWhere to Download Nemotron Cascade 2 30B A3B
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Related Models
Frequently Asked Questions
- How much VRAM does Nemotron Cascade 2 30B A3B need?
Nemotron Cascade 2 30B A3B requires 19.3 GB of VRAM at Q4_K_M, or 63.5 GB at BF16. Full 262K context adds up to 9.1 GB (28.4 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)
KV Cache + Overhead ≈ 9.5 GB (at full 262K context)
VRAM usage by quantization
Q4_K_M19.3 GBQ4_K_M + full context28.4 GB- Can NVIDIA GeForce RTX 4090 run Nemotron Cascade 2 30B A3B?
Yes, at Q5_K_L (23.3 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 Nemotron Cascade 2 30B A3B?
For Nemotron Cascade 2 30B A3B, Q4_K_M (19.3 GB) offers the best balance of quality and VRAM usage. Q4_K_L (19.7 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 9.1 GB.
VRAM requirement by quantization
IQ2_XXS9.1 GBQ2_K13.8 GBIQ4_XS17.3 GBQ4_K_M ★19.3 GBQ5_122.1 GBBF1663.5 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Nemotron Cascade 2 30B A3B on a Mac?
Nemotron Cascade 2 30B A3B requires at least 9.1 GB at IQ2_XXS, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run Nemotron Cascade 2 30B A3B locally?
Yes — Nemotron Cascade 2 30B A3B can run locally on consumer hardware. At Q4_K_M quantization it needs 19.3 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Nemotron Cascade 2 30B A3B?
At Q4_K_M, Nemotron Cascade 2 30B A3B can reach ~228 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~34 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 ÷ 19.3 × 0.65 = ~269 tok/s
Estimated speed at Q4_K_M (19.3 GB)
~269 tok/s~34 tok/s~269 tok/s~228 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Nemotron Cascade 2 30B A3B?
At Q4_K_M, the download is about 18.95 GB. The full-precision BF16 version is 63.16 GB. The smallest option (IQ2_XXS) is 8.68 GB.
- Which GPUs can run Nemotron Cascade 2 30B A3B?
8 consumer GPUs can run Nemotron Cascade 2 30B A3B at Q4_K_M (19.3 GB). Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX. 1 GPU have plenty of headroom for comfortable inference.
- Which devices can run Nemotron Cascade 2 30B A3B?
41 devices with unified memory can run Nemotron Cascade 2 30B A3B at Q4_K_M (19.3 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB), Beelink GTR9 Pro (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.