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.
Runs great on a 24 GB GPU
Runs from 8 GB (FP16 · 32K)Best on 24 GB (FP16 · ~160 tok/s · 32K)Macs from 8 GB (FP16 · ~18 tok/s)
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Moondream1
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve vikhyatk/moondream1 --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Other ways
each opens step-by-stepRun in cloud
Fits on RTX 3060 12GB (6 GB headroom) · FP16
- Generation speed
- ~57 tok/s
- generation speed
- Cost per 1M output tokens
- $0.34
- per 1M output tokens
How Much VRAM Does Moondream1 Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 4.1 GB | 7.7 GB | 16-bit · full — Full half-precision — baseline for inference | Fits: 32K context · ~160 tok/s |
Selected FP16
Full half-precision5.8GBat 16K context
- Weights
- 3.6 GB
- KV cache
- 2.0 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 18.2 GB free · ~160 tok/s
≥50 tok/s needs ≥314 GB/s · RTX 5090 ~285, RTX 3090 Ti ~160
Which Hardware 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. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run Moondream1, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), MacBook Air 13" M3 (8 GB).
≤ 11 GB
≤ 11 GB tier →fits · 2.2 GB free · up to 32K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~121Simulate output on RTX 3080RTX 2080 Ti~98Simulate output on RTX 2080 TiRTX 3070 Ti~97Simulate output on RTX 3070 TiM3*8 GB~18Simulate output on iMac 24" M3 (8 GB)Orin Nano~16Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~12Simulate output on iPhone 1720 GB
fits · 14.2 GB free · up to 32K ctx
1 GPU
RX 7900 XT~117Simulate output on RX 7900 XT32–40 GB
fits · 26.2 GB free · up to 32K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~285Simulate output on RTX 5090M5 Max36 GB~79Simulate output on Mac Studio M5 Max (36 GB)M532 GB~26Simulate output on MacBook Air 13" M5 (32 GB)Orin~33Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~22Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at FP16
Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Qwen 1 8BAlibaba | — | 1.9 GB | ~542 | same size |
| Gemma 3n E2B IT Litert LmGoogle | — | 3.1 GB | ~496 | same size |
| Qwen3 1.7B BaseAlibaba | — | 3.2 GB | ~417 | same size |
| DeepSeek R1 Distill Qwen 1.5BDeepSeek | — | 1.8 GB | ~461 | same size |
| MiniCPM 2B Sft BF16OpenBMB | — | 3 GB | ~291 | same size |
| Nemotron Labs Audex 2BNVIDIA | — | 6.1 GB | ~149 | same size |
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)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
VRAM usage by quantization
Can I run Moondream1 on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run Moondream1. Apple Silicon uses unified memory, so the model shares RAM with the system. At FP16 you need at least 4.1 GB of usable unified memory (RAM minus macOS overhead).
Can I run Moondream1 locally?
Yes — Moondream1 can run locally on consumer hardware. 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 ÷ 4.09 × 0.65 = ~1271 tok/s
Estimated speed at FP16 (4.1 GB)
Real-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?
52 consumer GPUs can run Moondream1 at FP16. 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 Moondream1?
163 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, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (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.