// Microsoft VibeVoice / Fara / Harrier · Embedding
harrier-oss-v1-270m: VRAM & local deployment
268M parameters. About 0.7 GB at 4-bit and 1.1 GB at BF16.
released 2026-03-30licence: Commercial OKmemory figures are estimates
01Specs
| Publisher | Microsoft · microsoft |
|---|---|
| Family / series | Microsoft VibeVoice / Fara / Harrier · harrier-oss |
| Type | Embedding (feature-extraction) |
| Parameters | 268M Source: counted from official safetensors weights |
| Released weights | BF16 · 0.5 GBdownload |
| Licence | MIT · Commercial OKPermissive licence (Apache-2.0 / MIT / CC-BY / OpenMDW): commercial use allowed. |
| Released | 2026-03-30 (Hugging Face repo created) |
02How much VRAM it needs (estimate)
Embedding models are small; memory grows with batch size and sequence length.
| Precision | Weights | Weights + overhead | Smallest GPU | Mac |
|---|---|---|---|---|
| BF16 / FP16 (original) | 0.5 GB | 1.1 GB | 8GB GPU | Mac 16GB |
| FP8 / INT8 / Q8_0 | 0.3 GB | 0.8 GB | 8GB GPU | Mac 16GB |
| 4-bit (Q4_K_M / AWQ / GPTQ-Int4) | 0.2 GB | 0.7 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.
- Transformers — mentioned in the official model card
- Sentence Transformers — mentioned in the official model card
04Official repositories & quantised builds
1 official repo(s) from microsoft.
- harrier-oss-v1-270m main
05Other Microsoft VibeVoice / Fara / Harrier models
All 12 →| Model | Params | 4-bit total | Released |
|---|---|---|---|
| harrier-oss-v1-0.6b · same series | 596M | 0.9 GB | 2026-03-30 |
| harrier-oss-v1-27b · same series | 27B | 18.5 GB | 2026-03-30 |
| VibeVoice-ASR-Streaming-1.5B | 2.81B | 2.4 GB | 2026-09-02 |
| VibeVoice-ASR-Streaming-7B | 8.67B | 6.3 GB | 2026-09-02 |
| Fara1.5-4B | 4.54B | 3.8 GB | 2026-07-17 |
| Fara1.5-27B | 27.4B | 19.3 GB | 2026-07-17 |
| Fara1.5-9B | 9.41B | 7.0 GB | 2026-05-12 |
| VibeVoice-ASR | 8.67B | 6.3 GB | 2026-01-21 |
| VibeVoice-Realtime-0.5B | 1.02B | 1.2 GB | 2025-12-04 |
| Fara-7B | 8.29B | 6.5 GB | 2025-10-30 |
06Sources
Data checked 2026-03-30. Parameters, context and licence are copied from the official repository; memory figures are our estimates.