Skip to content
English

Switch theme

// Ant Ling / Ring / Ming · Image generation

Ming-Image-0.1-Design: VRAM & local deployment

6.16B (MoE) parameters. About 4.6 GB at 4-bit and 14.0 GB at BF16.

released 2026-09-17licence: Commercial OKmemory figures are estimates

01Specs

PublisherAnt Group inclusionAI · inclusionAI
Family / seriesAnt Ling / Ring / Ming · Ming-Image-0.1-Design
TypeImage generation (text-to-image)
Parameters6.16B (MoE) Source: counted from official safetensors weights
Released weightsBF16 · 52.9 GBdownload
LicenceMIT · Commercial OKPermissive licence (Apache-2.0 / MIT / CC-BY / OpenMDW): commercial use allowed.
Released2026-09-17 (Hugging Face repo created)

02How much VRAM it needs (estimate)

Image models: memory depends on resolution, batch and which text encoders are kept on the GPU; Diffusers / ComfyUI can offload parts to CPU. The weight size below is the main transformer only.

PrecisionWeightsWeights + overheadSmallest GPUMac
BF16 / FP16 (original)12.3 GB 14.0 GB 16GB GPUMac 24GB
FP8 / INT8 / Q8_06.5 GB 7.7 GB 12GB GPUMac 16GB
4-bit (Q4_K_M / AWQ / GPTQ-Int4)3.7 GB 4.6 GB 8GB GPUMac 16GB

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.

Which inference engine to choose →

04Official repositories & quantised builds

1 official repo(s) from inclusionAI.

05Other Ant Ling / Ring / Ming models

All 29 →
ModelParams4-bit totalReleased
Ling-3.0-tiny-UBTree183M1.0 GB2026-10-21
Ling-3.0-flash-UBTree482M1.5 GB2026-10-14
Ming-3.0-asr-tiny8.87B6.4 GB2026-10-14
Ling-3.1-flash560B / 25B375 GB2026-10-13
Ming-3.0-tts-0.5B1.48B1.5 GB2026-09-22
Ming-3.0-tts-tiny8.98B / 1.3B6.5 GB2026-09-22
Ling-3.0-flash-VL124B / 5.5B83.6 GB2026-09-04
Ming-3.0-audio-flash126B / 6.5B84.5 GB2026-09-03

06Sources

Data checked 2026-10-14. Parameters, context and licence are copied from the official repository; memory figures are our estimates.

Data updated: Self-host open models(UTC+8)