// Kimi · Text LLM
Moonlight-16B-A3B-Instruct: VRAM & local deployment
16B total · 3B active (MoE) parameters. About 11.4 GB at 4-bit and 35.9 GB at BF16 with one 8K-token request.
released 2025-02-22licence: Commercial OKmemory figures are estimates
01Specs
| Publisher | Moonshot AI · moonshotai |
|---|---|
| Family / series | Kimi · Moonlight |
| Type | Text LLM (text-generation) |
| Parameters | 16B total · 3B active (MoE) Source: counted from official safetensors weights |
| Context length | 8K tokens (8,192)max_position_embeddings in config.json |
| Architecture | 27 layers · MLA · MoE |
| Released weights | BF16 · 31.9 GBdownload |
| Licence | MIT · Commercial OKPermissive licence (Apache-2.0 / MIT / CC-BY / OpenMDW): commercial use allowed. |
| Released | 2025-02-22 (Hugging Face repo created) |
02How much VRAM it needs (estimate)
Total = weights + 10% + 0.5GB overhead + KV cache for one request (FP16 KV). More concurrent users multiply the KV column.
| Precision | Weights | Total @ 8K | Smallest GPU | Mac |
|---|---|---|---|---|
| BF16 / FP16 (original) | 31.9 GB | 35.9 GB | 2 × RTX 5090 (64GB) | Mac 64GB |
| FP8 / INT8 / Q8_0 | 17.0 GB | 19.4 GB | RTX 4090 24GB | Mac 36GB |
| 4-bit (Q4_K_M / AWQ / GPTQ-Int4) | 9.7 GB | 11.4 GB | 16GB GPU | Mac 24GB |
KV cache per request: 8K 0.3 GB
Bits per weight: BF16 16, FP8 8.5, 4-bit 4.85. “Fits” = total ≤ 90% of memory; Mac GPU can use ~2/3 of unified memory (≤36GB) or ~3/4 (larger). For MoE, all experts must be in memory, so size by total parameters. Method →
03How to run it
Only runtimes the publisher or the runtime’s official library names for this model.
- vLLM — mentioned in the official model card
- SGLang — mentioned in the official model card
- Transformers — mentioned in the official model card
04Official repositories & quantised builds
2 official repo(s) from moonshotai.
- Moonlight-16B-A3B-Instruct Instruct
- Moonlight-16B-A3B main
05Other Kimi models
All 14 →| Model | Params | 4-bit total | Released |
|---|---|---|---|
| Kimi-K3 | 2.8T / 104B | 1.87 TB | 2026-06-13 |
| Kimi-K2.7-Code | 1T / 32B | 668 GB | 2026-06-11 |
| Kimi-K2.6 | 1T / 32B | 668 GB | 2026-04-14 |
| Kimi-K2.5 | 1T / 32B | 668 GB | 2026-01-01 |
| Kimi-K2-Thinking | 1T / 32B | 668 GB | 2025-11-04 |
| Kimi-Linear-48B-A3B-Instruct | 49.1B / 3B | 33.3 GB | 2025-10-30 |
| Kimi-K2-Instruct-0905 | 1T / 32B | 668 GB | 2025-09-03 |
| Kimi-K2-Instruct | 1T / 32B | 668 GB | 2025-07-11 |
06Sources
Data checked 2026-01-30. Parameters, context and licence are copied from the official repository; memory figures are our estimates.