Biren BR100
VRAM
64 GB
Memory
HBM2e
Bandwidth
1600 GB/s
TDP
550W
Suitable Workloads
Medium Language Models
Inference for models up to 70B parameters
Deep Learning Training
High-performance training for neural networks
Enterprise Deployment
Designed for 24/7 datacenter operations
Key Highlights
- Built on Biren BR100 architecture
- OAM form factor
Memory
Compute Performance
Architecture
Power & Physical
Interconnect
Notes
China market. Specs from Biren's own Hot Chips 34 disclosure: 1024 TFLOPS BF16, 2048 TOPS INT8, 64GB HBM2e at 1.6 TB/s. Volume production subsequently constrained by US export controls; successor SKUs (BR104) shipped in its place.
Models That May Fit on Biren BR100
Estimates based on INT8 quantization. Actual fit depends on framework and batch size.
Explore More
Added Jul 30, 2026
Last updated: Jul 30, 2026
Your AI stack shouldn't stand still.
Every month new models become cheaper, faster, and more capable. Inferbase ensures your application automatically benefits without changing a single API call.