Huawei Atlas 300V
Overview
The Huawei Atlas 300V is a video analysis card built on a down-binned Ascend 310P, rated at 100 TOPS INT8 and 50 TFLOPS FP16. Those figures are five sevenths of the 140 TOPS and 70 TFLOPS that the Atlas 300I Pro and Atlas 300V Pro achieve from the same chip at the same 72 watts, the same 204.8 GB/s of LPDDR4X bandwidth and the same board size, so this is a genuine clock or core bin rather than a rounding or transcription difference. The card pairs 24 GB of LPDDR4X with an eight-core 1.9 GHz host CPU and supports ECC, and its media block handles 80 channels of 1080p30 decode, or 10 channels of 4K60, plus 24 channels of 1080p30 encode.
Performance
Peak theoretical throughput by precision type
| Precision | Peak |
|---|---|
FP64 | No verified data available |
FP32 | No verified data available |
TF32 | No verified data available |
BF16 | No verified data available |
FP16 16-bit floating point | 50TFLOPS |
FP8 | No verified data available |
FP6 | No verified data available |
FP4 | No verified data available |
INT8 8-bit integer | 100TOPS |
Dense peak divided by accelerator TDP. Board power only: excludes host CPUs, networking, cooling and facility overhead. TDP for this part: 72 W.
The Atlas 300V in the GPU landscape
Peak FP16 TFLOPS (dense) against TDP, single-GPU parts tracked by Flopper
Higher and further left is better: more half-precision throughput for less power.
Specifications
Architecture
Da Vinci
Form Factor
PCIe
Launch Year
2022
Process Node
No verified data available
Memory
24 GB LPDDR4X
Bandwidth
204.8 GB/s
TDP
72 W
Max power (Flopper estimate)
~83 W est. Flopper estimate: 72 W TDP x 1.15. The vendor publishes no maximum board power for this part.
Spec Confidence
Official
Full Specifications
| Chip Design | |
|---|---|
| Chiplets | 1 |
| Memory | |
| Memory | 24 GB |
| Memory Type | LPDDR4X |
| Bandwidth | 205 GB/s |
| Interface Width | No verified data available |
| Interconnect & I/O | |
| PCIe | 4.0 x16 |
| Power & Thermal | |
| TDP | 72 W |
| Max power (Flopper estimate) | ~83 W est. |
| Enterprise Features | |
| ECC Memory | Yes |
| Compute APIs | CANN, MindSpore, MindX, PyTorch (torch_npu), ACL |
| Physical & Media | |
| Card Length | 169.5 mm |
| General | |
| Form Factor | PCIe |
| Architecture | Da Vinci |
| Process Node | No verified data available |
| Launch Year | 2022 |
Datasheet & Resources
Flopper Datasheet
Huawei Atlas 300V specifications, generated from our database. Printable.
Vendor product page
Huawei documentation for the Atlas 300V
Atlas 300V 视频解析卡 规格 (100 TOPS INT8, 50 TFLOPS FP16, 24GB LPDDR4X)
Huawei · Latest version
Huawei Ascend Developer Documentation
CANN guides, MindSpore, Da Vinci
Data Provenance
Every figure traced to a source
Primary Source
- Publisher
- Huawei
- Published
- No verified data available
Data Quality
- Spec confidence
- Official
- Clock basis
- Boost
- Core precisions with figures
- 2 of 9
- Normalization
- All values in TFLOPS
Compare cloud providers offering on-demand GPU instances for AI training, inference, and HPC workloads.
Browse GPU Cloud ProvidersSimilar GPUs
Frequently Asked Questions
How many TFLOPS does the Huawei Atlas 300V have?
The Huawei Atlas 300V delivers 50 TFLOPS FP16 at peak. Flopper does not currently have verified FP32 and FP8 throughput figures for it.
What is the power consumption of the Huawei Atlas 300V?
The Huawei Atlas 300V has a TDP (Thermal Design Power) rating of 72 watts.
How much memory does the Huawei Atlas 300V have?
The Huawei Atlas 300V is equipped with 24 GB of memory with 204.8 GB/s of memory bandwidth.
What architecture is the Huawei Atlas 300V based on?
The Huawei Atlas 300V is based on the Da Vinci architecture, launched in 2022.
Stay Updated on GPU Releases
Get notified when new GPUs are added or specifications are updated.
No spam, unsubscribe anytime.