Moonlight 16B A3B Instruct — Hardware Requirements & GPU Compatibility
Chat
Moonlight 16B A3B Instruct is a 16.0B-parameter open language model from Moonshot AI in the Moonlight family. It supports a context window of up to 8,192 tokens. At Q4_K_M it needs about 10.33 GB of VRAM — see which GPUs and Macs can run it below.
109.0K downloads
194 likesSpecifications
- Publisher
- Moonshot AI
- Family
- Moonlight
- Parameters
- 16.0B
- Architecture
- DeepseekV3ForCausalLM
- Context Length
- 8,192 tokens
- Vocabulary Size
- 163,840
- Release Date
- 2026-01-30
- License
- MIT
Get Started
HuggingFace
How Much VRAM Does Moonlight 16B A3B Instruct Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 7.5 GB | 8.9 GB | 6.78 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 7.7 GB | 9.1 GB | 6.98 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 8.5 GB | 9.9 GB | 7.78 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 8.7 GB | 10.1 GB | 7.98 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 10.3 GB | 11.7 GB | 9.58 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 12.1 GB | 13.5 GB | 11.37 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 13.9 GB | 15.3 GB | 13.17 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 16.7 GB | 18.1 GB | 15.96 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run Moonlight 16B A3B Instruct?
Q4_K_M · 10.3 GBMoonlight 16B A3B Instruct (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. 27 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 Instruct?
Q4_K_M · 10.3 GB27 devices with unified memory can run Moonlight 16B A3B Instruct, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomRelated Models
Derivatives (3)
Frequently Asked Questions
- How much VRAM does Moonlight 16B A3B Instruct need?
Moonlight 16B A3B Instruct requires 10.3 GB of VRAM at Q4_K_M, or 16.7 GB at Q8_0. 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- What's the best quantization for Moonlight 16B A3B Instruct?
For Moonlight 16B A3B Instruct, Q4_K_M (10.3 GB) offers the best balance of quality and VRAM usage. Q5_0 (10.7 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 5.1 GB.
VRAM requirement by quantization
IQ2_XXS5.1 GBIQ3_XS7.3 GBQ3_K_M8.5 GBQ4_K_M ★10.3 GBQ5_010.7 GBQ8_016.7 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Moonlight 16B A3B Instruct on a Mac?
Moonlight 16B A3B Instruct requires at least 5.1 GB at IQ2_XXS, 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 Instruct locally?
Yes — Moonlight 16B A3B Instruct 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 Instruct?
At Q4_K_M, Moonlight 16B A3B Instruct can reach ~282 tok/s on AMD Instinct MI300X. 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: AMD Instinct MI300X → 5300 ÷ 10.3 × 0.55 = ~282 tok/s
Estimated speed at Q4_K_M (10.3 GB)
~282 tok/s~63 tok/s~211 tok/s~175 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 Instruct?
At Q4_K_M, the download is about 9.58 GB. The full-precision Q8_0 version is 15.96 GB. The smallest option (IQ2_XXS) is 4.39 GB.
- Which GPUs can run Moonlight 16B A3B Instruct?
27 consumer GPUs can run Moonlight 16B A3B Instruct 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. 17 GPUs have plenty of headroom for comfortable inference.
- Which devices can run Moonlight 16B A3B Instruct?
27 devices with unified memory can run Moonlight 16B A3B Instruct at Q4_K_M (10.3 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.