Wizard Vicuna 30B Uncensored — Hardware Requirements & GPU Compatibility
Chat
Wizard Vicuna 30B Uncensored is a 30B-parameter open language model from QuixiAI in the Vicuna family. It supports a context window of up to 2,048 tokens. At BF16 it needs about 66.00 GB of VRAM — see which GPUs and Macs can run it below.
985 downloads
164 likesSpecifications
- Publisher
- QuixiAI
- Family
- Vicuna
- Parameters
- 30B
- Architecture
- LlamaForCausalLM
- Context Length
- 2,048 tokens
- Vocabulary Size
- 32,000
- Release Date
- 2024-05-20
- License
- Other
Get Started
HuggingFace
How Much VRAM Does Wizard Vicuna 30B Uncensored Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 66 GB | — | 60.00 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run Wizard Vicuna 30B Uncensored?
BF16 · 66 GBWizard Vicuna 30B Uncensored (BF16) requires 66 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 86+ GB is recommended. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run Wizard Vicuna 30B Uncensored?
BF16 · 66 GB5 devices with unified memory can run Wizard Vicuna 30B Uncensored, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Related Models
Frequently Asked Questions
- How much VRAM does Wizard Vicuna 30B Uncensored need?
Wizard Vicuna 30B Uncensored requires 66 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 30B × 16 bits ÷ 8 = 60 GB
KV Cache + Overhead ≈ 6 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
BF1666.0 GB- Can NVIDIA GeForce RTX 5090 run Wizard Vicuna 30B Uncensored?
No — Wizard Vicuna 30B Uncensored requires at least 66 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
- Can I run Wizard Vicuna 30B Uncensored on a Mac?
Wizard Vicuna 30B Uncensored requires at least 66 GB at BF16, 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 Wizard Vicuna 30B Uncensored locally?
Yes — Wizard Vicuna 30B Uncensored can run locally on consumer hardware. At BF16 quantization it needs 66 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Wizard Vicuna 30B Uncensored?
At BF16, Wizard Vicuna 30B Uncensored can reach ~44 tok/s on AMD Instinct MI300X. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: AMD Instinct MI300X → 5300 ÷ 66.0 × 0.55 = ~44 tok/s
Estimated speed at BF16 (66 GB)
~44 tok/s~33 tok/s~27 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Wizard Vicuna 30B Uncensored?
At BF16, the download is about 60.00 GB.
- Which GPUs can run Wizard Vicuna 30B Uncensored?
No single consumer GPU has enough VRAM to run Wizard Vicuna 30B Uncensored at BF16 (66 GB). Multi-GPU or professional hardware is required.
- Which devices can run Wizard Vicuna 30B Uncensored?
5 devices with unified memory can run Wizard Vicuna 30B Uncensored at BF16 (66 GB), including Mac Pro M2 Ultra (192 GB), Mac Studio M2 Ultra (192 GB), Mac Studio M4 Max (128 GB), NVIDIA DGX A100 640GB. Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.