Cagliostro v3 — Hardware Requirements & GPU Compatibility
Chat
Cagliostro v3 is a 146M-parameter open language model from bench-labs. It supports a context window of up to 2,048 tokens. At BF16 it needs about 0.67 GB of VRAM — see which GPUs and Macs can run it below.
1.3K downloads
31 likesSpecifications
- Publisher
- bench-labs
- Parameters
- 146M
- Architecture
- CagliostroForCausalLM
- Context Length
- 2,048 tokens
- Vocabulary Size
- 32,768
- Release Date
- 2026-09-11
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Cagliostro v3 Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16est. | 16.00 | 0.7 GB | — | 0.29 GB | Brain floating point 16 — preferred for training |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run Cagliostro v3?
BF16 · 0.7 GBCagliostro v3 (BF16) requires 0.7 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 1+ GB is recommended. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run Cagliostro v3?
BF16 · 0.7 GB59 devices with unified memory can run Cagliostro v3, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomFrequently Asked Questions
- How much VRAM does Cagliostro v3 need?
Cagliostro v3 requires 0.7 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 146M × 16 bits ÷ 8 = 0.3 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
BF160.7 GB- Can I run Cagliostro v3 on a Mac?
Cagliostro v3 requires at least 0.7 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 Cagliostro v3 locally?
Yes — Cagliostro v3 can run locally on consumer hardware. At BF16 quantization it needs 0.7 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Cagliostro v3?
At BF16, Cagliostro v3 can reach ~7164 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~978 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 ÷ 0.7 × 0.65 = ~7761 tok/s
Estimated speed at BF16 (0.7 GB)
~7761 tok/s~978 tok/s~7761 tok/s~7164 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Cagliostro v3?
At BF16, the download is about 0.29 GB.
- Which GPUs can run Cagliostro v3?
52 consumer GPUs can run Cagliostro v3 at BF16 (0.7 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 52 GPUs have plenty of headroom for comfortable inference.
- Which devices can run Cagliostro v3?
59 devices with unified memory can run Cagliostro v3 at BF16 (0.7 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Apple iPhone 17 Pro, Asus ROG Flow Z13 (2025, 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.