Moonlight 16B A3B — Hardware Requirements & GPU Compatibility
Chat
Moonlight 16B A3B is a compact Mixture-of-Experts model from Moonshot AI that packs 16 billion total parameters while activating only around 3 billion per token. This efficient sparse design lets it punch well above its active parameter count, delivering surprisingly strong chat performance for its effective inference cost. The small active parameter count means Moonlight runs briskly on modest hardware, fitting comfortably on GPUs with 8–12 GB of VRAM at common quantization levels. It is an appealing choice for users who want MoE-level performance diversity without the heavy memory footprint typically associated with mixture models.
72.7K downloads
109 likesSpecifications
- Publisher
- Moonshot AI
- Family
- Moonlight
- Parameters
- 16.0B
- Architecture
- DeepseekV3ForCausalLM
- Context Length
- 8,192 tokens
- Vocabulary Size
- 163,840
- Release Date
- 2025-02-22
- License
- MIT
Get Started
HuggingFace
How Much VRAM Does Moonlight 16B A3B Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_Kest. | 3.40 | 7.5 GB | 8.9 GB | 6.78 GB | 2-bit quantization with K-quant improvements |
| Q3_K_Mest. | 3.90 | 8.5 GB | 9.9 GB | 7.78 GB | 3-bit medium quantization |
| Q4_K_Mest. | 4.80 | 10.3 GB | 11.7 GB | 9.58 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_Mest. | 5.70 | 12.1 GB | 13.5 GB | 11.37 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_Kest. | 6.60 | 13.9 GB | 15.3 GB | 13.17 GB | 6-bit quantization, very good quality |
| Q8_0est. | 8.00 | 16.7 GB | 18.1 GB | 15.96 GB | 8-bit quantization, near-lossless |
| BF16est. | 16.00 | 32.7 GB | 34.0 GB | 31.92 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 Moonlight 16B A3B?
Q4_K_M · 10.3 GBMoonlight 16B A3B (Q4_K_M) requires 10.3 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 14+ GB is recommended. Using the full 8K context window can add up to 1.4 GB, bringing total usage to 11.7 GB. 37 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3080 Ti.
Runs great
— Plenty of headroom
Decent
— Enough VRAM, may be tightWhich Devices Can Run Moonlight 16B A3B?
Q4_K_M · 10.3 GB48 devices with unified memory can run Moonlight 16B A3B, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, NVIDIA Jetson Orin NX 16GB.
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightRelated Models
Frequently Asked Questions
- How much VRAM does Moonlight 16B A3B need?
Moonlight 16B A3B requires 10.3 GB of VRAM at Q4_K_M, or 32.7 GB at BF16. Full 8K context adds up to 1.4 GB (11.7 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 16.0B × 4.8 bits ÷ 8 = 9.6 GB
KV Cache + Overhead ≈ 0.7 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 2.1 GB (at full 8K context)
VRAM usage by quantization
Q4_K_M10.3 GBQ4_K_M + full context11.7 GB- Can NVIDIA GeForce RTX 4090 run Moonlight 16B A3B?
Yes, at Q8_0 (16.7 GB) or lower. Higher quantizations like BF16 (32.7 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
- What's the best quantization for Moonlight 16B A3B?
For Moonlight 16B A3B, Q4_K_M (10.3 GB) offers the best balance of quality and VRAM usage. Q5_K_M (12.1 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 7.5 GB.
VRAM requirement by quantization
Q2_K7.5 GBQ4_K_M ★10.3 GBQ5_K_M12.1 GBQ6_K13.9 GBQ8_016.7 GBBF1632.7 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Moonlight 16B A3B on a Mac?
Moonlight 16B A3B requires at least 7.5 GB at Q2_K, 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 Moonlight 16B A3B locally?
Yes — Moonlight 16B A3B can run locally on consumer hardware. At Q4_K_M quantization it needs 10.3 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Moonlight 16B A3B?
At Q4_K_M, Moonlight 16B A3B can reach ~426 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~63 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 ÷ 10.3 × 0.65 = ~503 tok/s
Estimated speed at Q4_K_M (10.3 GB)
~503 tok/s~63 tok/s~503 tok/s~426 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Moonlight 16B A3B?
At Q4_K_M, the download is about 9.58 GB. The full-precision BF16 version is 31.92 GB. The smallest option (Q2_K) is 6.78 GB.
- Which GPUs can run Moonlight 16B A3B?
37 consumer GPUs can run Moonlight 16B A3B at Q4_K_M (10.3 GB). Top options include AMD Radeon RX 6800, AMD Radeon RX 6800 XT, AMD Radeon RX 6900 XT, AMD Radeon RX 6700 XT. 26 GPUs have plenty of headroom for comfortable inference.
- Which devices can run Moonlight 16B A3B?
52 devices with unified memory can run Moonlight 16B A3B at Q4_K_M (10.3 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.