MagicPrompt Stable Diffusion — Hardware Requirements & GPU Compatibility
Chat
MagicPrompt Stable Diffusion is a 137M-parameter open language model from Gustavosta. It supports a context window of up to 1,024 tokens. At BF16 it needs about 0.30 GB of VRAM — see which GPUs and Macs can run it below.
8.8K downloads
737 likesSpecifications
- Publisher
- Gustavosta
- Parameters
- 137M
- Architecture
- GPT2LMHeadModel
- Context Length
- 1,024 tokens
- Vocabulary Size
- 50,257
- Release Date
- 2023-07-09
- License
- MIT
Get Started
HuggingFace
How Much VRAM Does MagicPrompt Stable Diffusion Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 0.3 GB | — | 0.27 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run MagicPrompt Stable Diffusion?
BF16 · 0.3 GBMagicPrompt Stable Diffusion (BF16) requires 0.3 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 1+ GB is recommended. 35 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run MagicPrompt Stable Diffusion?
BF16 · 0.3 GB33 devices with unified memory can run MagicPrompt Stable Diffusion, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomRelated Models
Frequently Asked Questions
- How much VRAM does MagicPrompt Stable Diffusion need?
MagicPrompt Stable Diffusion requires 0.3 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 137M × 16 bits ÷ 8 = 0.3 GB
VRAM usage by quantization
BF160.3 GB- Can I run MagicPrompt Stable Diffusion on a Mac?
MagicPrompt Stable Diffusion requires at least 0.3 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 MagicPrompt Stable Diffusion locally?
Yes — MagicPrompt Stable Diffusion can run locally on consumer hardware. At BF16 quantization it needs 0.3 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is MagicPrompt Stable Diffusion?
At BF16, MagicPrompt Stable Diffusion can reach ~9717 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~2184 tok/s. 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 ÷ 0.3 × 0.55 = ~9717 tok/s
Estimated speed at BF16 (0.3 GB)
~9717 tok/s~2184 tok/s~7263 tok/s~6008 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of MagicPrompt Stable Diffusion?
At BF16, the download is about 0.27 GB.
- Which GPUs can run MagicPrompt Stable Diffusion?
35 consumer GPUs can run MagicPrompt Stable Diffusion at BF16 (0.3 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 35 GPUs have plenty of headroom for comfortable inference.
- Which devices can run MagicPrompt Stable Diffusion?
33 devices with unified memory can run MagicPrompt Stable Diffusion at BF16 (0.3 GB), including Mac Mini M4 (16 GB), Mac Mini M4 (32 GB), Mac Mini M4 Pro (24 GB), Mac Mini M4 Pro (48 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.