Skip to content
English

Switch theme

// Ant Ling / Ring / Ming · Speech-to-text

Ming-3.0-asr-tiny: VRAM & local deployment

8.87B (MoE) parameters. About 6.4 GB at 4-bit and 20.0 GB at BF16.

released 2026-10-14licence: Commercial OKmemory figures are estimates

01Specs

PublisherAnt Group inclusionAI · inclusionAI
Family / seriesAnt Ling / Ring / Ming · Ming-3.0-asr-tiny
TypeSpeech-to-text (automatic-speech-recognition)
Parameters8.87B (MoE) Source: counted from official safetensors weights
Released weightsBF16 · 17.7 GBdownload
LicenceMIT · Commercial OKPermissive licence (Apache-2.0 / MIT / CC-BY / OpenMDW): commercial use allowed.
Released2026-10-14 (Hugging Face repo created)

02How much VRAM it needs (estimate)

Speech models are small; the weight size is close to the total memory needed.

PrecisionWeightsWeights + overheadSmallest GPUMac
BF16 / FP16 (original)17.7 GB 20.0 GB RTX 4090 24GBMac 36GB
FP8 / INT8 / Q8_09.4 GB 10.9 GB 16GB GPUMac 24GB
4-bit (Q4_K_M / AWQ / GPTQ-Int4)5.4 GB 6.4 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
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
Ming-Image-0.1-Design6.16B4.6 GB2026-09-17
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 2026-10-21. Parameters, context and licence are copied from the official repository; memory figures are our estimates.

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