// 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
| Publisher | Moonshot AI · moonshotai |
|---|---|
| Family / series | Kimi · Kimi-Audio |
| Type | Text-to-speech / audio (text-to-speech) |
| Parameters | 9.77B Source: counted from official safetensors weights |
| Released weights | BF16 · 19.5 GBdownload |
| Licence | MIT · Commercial OKPermissive licence (Apache-2.0 / MIT / CC-BY / OpenMDW): commercial use allowed. |
| Released | 2025-04-25 (Hugging Face repo created) |
02How much VRAM it needs (estimate)
Audio models are small; the weight size is close to the total memory needed.
| Precision | Weights | Weights + overhead | Smallest GPU | Mac |
|---|---|---|---|---|
| BF16 / FP16 (original) | 19.5 GB | 22.0 GB | RTX 5090 32GB | Mac 64GB |
| FP8 / INT8 / Q8_0 | 10.4 GB | 11.9 GB | 16GB GPU | Mac 24GB |
| 4-bit (Q4_K_M / AWQ / GPTQ-Int4) | 5.9 GB | 7.0 GB | 8GB GPU | Mac 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.
04Official repositories & quantised builds
1 official repo(s) from moonshotai.
- Kimi-Audio-7B-Instruct Instruct
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 2025-05-29. Parameters, context and licence are copied from the official repository; memory figures are our estimates.