WizardLM 13B Uncensored — Hardware Requirements & GPU Compatibility
Chat
WizardLM 13B Uncensored is a 13B-parameter open language model from QuixiAI. It supports a context window of up to 2,048 tokens. At FP16 it needs about 28.60 GB of VRAM — see which GPUs and Macs can run it below.
2.2K downloads
666 likesSpecifications
- Publisher
- QuixiAI
- Parameters
- 13B
- Architecture
- LlamaForCausalLM
- Context Length
- 2,048 tokens
- Vocabulary Size
- 32,001
- Release Date
- 2023-05-12
- License
- Other
Get Started
HuggingFace
How Much VRAM Does WizardLM 13B Uncensored Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| FP16 | 16.00 | 28.6 GB | — | 26.00 GB | Full half-precision — baseline for inference |
Which GPUs Can Run WizardLM 13B Uncensored?
FP16 · 28.6 GBWizardLM 13B Uncensored (FP16) requires 28.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 38+ GB is recommended. 1 GPU can run it, including NVIDIA GeForce RTX 5090.
All compatible consumer-level GPUs are running near their VRAM limit. You may also want to consider professional GPUs (e.g., NVIDIA A100, H100) which offer significantly more VRAM. For more headroom and better throughput, consider a multi-GPU configuration with tensor parallelism (supported by tools like vLLM, llama.cpp, or text-generation-inference).
Decent
— Enough VRAM, may be tightWhich Devices Can Run WizardLM 13B Uncensored?
FP16 · 28.6 GB15 devices with unified memory can run WizardLM 13B Uncensored, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Studio M4 Max (36 GB).
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightRelated Models
Frequently Asked Questions
- How much VRAM does WizardLM 13B Uncensored need?
WizardLM 13B Uncensored requires 28.6 GB of VRAM at FP16.
VRAM = Weights + KV Cache + Overhead
Weights = 13B × 16 bits ÷ 8 = 26 GB
KV Cache + Overhead ≈ 2.6 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
FP1628.6 GB- Can I run WizardLM 13B Uncensored on a Mac?
WizardLM 13B Uncensored requires at least 28.6 GB at FP16, 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 WizardLM 13B Uncensored locally?
Yes — WizardLM 13B Uncensored can run locally on consumer hardware. At FP16 quantization it needs 28.6 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is WizardLM 13B Uncensored?
At FP16, WizardLM 13B Uncensored can reach ~102 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 ÷ 28.6 × 0.55 = ~102 tok/s
Estimated speed at FP16 (28.6 GB)
~102 tok/s~76 tok/s~63 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of WizardLM 13B Uncensored?
At FP16, the download is about 26.00 GB.
- Which GPUs can run WizardLM 13B Uncensored?
1 consumer GPU can run WizardLM 13B Uncensored at FP16 (28.6 GB). Top options include NVIDIA GeForce RTX 5090.
- Which devices can run WizardLM 13B Uncensored?
15 devices with unified memory can run WizardLM 13B Uncensored at FP16 (28.6 GB), including Mac Mini M4 (32 GB), Mac Mini M4 Pro (48 GB), Mac Pro M2 Ultra (192 GB), Mac Studio M2 Ultra (192 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.