Skip to content
English

Switch theme

// Kimi · Text-to-speech / audio

Kimi-Audio-7B-Instruct: VRAM & local deployment

9.77B parameters. About 7.0 GB at 4-bit and 22.0 GB at BF16.

released 2025-04-25licence: Commercial OKmemory figures are estimates

01Specs

PublisherMoonshot AI · moonshotai
Family / seriesKimi · Kimi-Audio
TypeText-to-speech / audio (text-to-speech)
Parameters9.77B Source: counted from official safetensors weights
Released weightsBF16 · 19.5 GBdownload
LicenceMIT · Commercial OKPermissive licence (Apache-2.0 / MIT / CC-BY / OpenMDW): commercial use allowed.
Released2025-04-25 (Hugging Face repo created)

02How much VRAM it needs (estimate)

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

PrecisionWeightsWeights + overheadSmallest GPUMac
BF16 / FP16 (original)19.5 GB 22.0 GB RTX 5090 32GBMac 64GB
FP8 / INT8 / Q8_010.4 GB 11.9 GB 16GB GPUMac 24GB
4-bit (Q4_K_M / AWQ / GPTQ-Int4)5.9 GB 7.0 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.

The official card does not name a runtime; see the repository.

Which inference engine to choose →

04Official repositories & quantised builds

1 official repo(s) from moonshotai.

05Other Kimi models

All 14 →
ModelParams4-bit totalReleased
Kimi-K32.8T / 104B1.87 TB2026-06-13
Kimi-K2.7-Code1T / 32B668 GB2026-06-11
Kimi-K2.61T / 32B668 GB2026-04-14
Kimi-K2.51T / 32B668 GB2026-01-01
Kimi-K2-Thinking1T / 32B668 GB2025-11-04
Kimi-Linear-48B-A3B-Instruct49.1B / 3B33.3 GB2025-10-30
Kimi-K2-Instruct-09051T / 32B668 GB2025-09-03
Kimi-K2-Instruct1T / 32B668 GB2025-07-11

06Sources

Data checked 2025-05-29. Parameters, context and licence are copied from the official repository; memory figures are our estimates.

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