Microsoft
Fara 1.5 27B
Microsoft model
Model Summary
Family
Fara 1.5
Version
1.5
Parameters
27.4B (est.)
Parameter counts for closed models are estimates; vendors rarely publish exact sizes.
VRAM Requirements by Quantization
Memory needed to serve Fara 1.5 27B for inference, including a 20% overhead for activations and KV cache.
| Precision | VRAM needed | Smallest single GPU that fits |
|---|---|---|
| INT4 (4-bit) | 15.31 GB | NVIDIA P100 SXM2 (16 GB) |
| INT8 (8-bit) | 30.62 GB | NVIDIA V100 SXM2 32GB (32 GB) |
| FP16 (16-bit) | 61.24 GB | NVIDIA H100 SXM5 (80 GB) |
| FP32 (32-bit) | 122.49 GB | AMD Instinct MI250X (128 GB) |
Recommended GPU Configurations
Cheapest on-demand configurations to serve Fara 1.5 27B at 8-bit (31 GB VRAM).
2x NVIDIA T4
32 GB total VRAM · Turing
~$1.00/h
2x NVIDIA P100 SXM2
32 GB total VRAM · Pascal
~$1.20/h
1x NVIDIA A40
48 GB total VRAM · Ampere
~$1.80/h
Quick GPU Planning
Use the calculator pre-filled with this exact version to estimate memory, speed, and compute requirements in a few clicks.
Access Pre-filled CalculatorFrequently Asked Questions
How much VRAM do you need to run Fara 1.5 27B?
With an estimated 27.4B parameters, Fara 1.5 27B needs roughly 31 GB of VRAM in 8-bit (INT8), 15 GB in 4-bit, and 61 GB in FP16, including a 20% overhead for activations and KV cache.
Which GPUs can run Fara 1.5 27B?
At 8-bit quantization, the most cost-effective option is 2x NVIDIA T4 (32 GB combined VRAM, around $1.00/hour on-demand). Higher-end cards like the NVIDIA B200 or AMD MI355X reduce the GPU count needed.
Can Fara 1.5 27B run on a single GPU?
Yes. In 8-bit, a single NVIDIA V100 SXM2 32GB (32 GB) fits the model.
How much does it cost to serve Fara 1.5 27B in the cloud?
Renting 2x T4 costs on the order of $1.00/hour, i.e. about $730/month running 24/7. Actual prices vary by provider and commitment; spot and reserved capacity can be significantly cheaper.
Deploy on a GPU cloud
Rent 2x T4 by the hour instead of buying hardware.
