Moondream1 — Hardware Requirements & GPU Compatibility
Chat
Moondream1 is a 1.9B-parameter open language model from vikhyatk. At FP16 it needs about 4.09 GB of VRAM — see which GPUs and Macs can run it below.
15.5K downloads
487 likesSpecifications
- Publisher
- vikhyatk
- Parameters
- 1.9B
- Architecture
- Moondream
- Release Date
- 2024-01-20
Get Started
HuggingFace
How Much VRAM Does Moondream1 Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| FP16est. | 16.00 | 4.1 GB | — | 3.71 GB | Full half-precision — baseline for inference |
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 Moondream1?
FP16 · 4.1 GBMoondream1 (FP16) requires 4.1 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 6+ GB is recommended. 50 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run Moondream1?
FP16 · 4.1 GB59 devices with unified memory can run Moondream1, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, iPhone 17.
Runs great
— Plenty of headroom
Decent
— Enough memory, may be tightRelated Models
Frequently Asked Questions
- How much VRAM does Moondream1 need?
Moondream1 requires 4.1 GB of VRAM at FP16.
VRAM = Weights + KV Cache + Overhead
Weights = 1.9B × 16 bits ÷ 8 = 3.7 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
FP164.1 GB- Can I run Moondream1 on a Mac?
Moondream1 requires at least 4.1 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 Moondream1 locally?
Yes — Moondream1 can run locally on consumer hardware. At FP16 quantization it needs 4.1 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Moondream1?
At FP16, Moondream1 can reach ~1174 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~160 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 ÷ 4.1 × 0.65 = ~1271 tok/s
Estimated speed at FP16 (4.1 GB)
~1271 tok/s~160 tok/s~1271 tok/s~1174 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Moondream1?
At FP16, the download is about 3.71 GB.
- Which GPUs can run Moondream1?
50 consumer GPUs can run Moondream1 at FP16 (4.1 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 50 GPUs have plenty of headroom for comfortable inference.
- Which devices can run Moondream1?
59 devices with unified memory can run Moondream1 at FP16 (4.1 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.