DEPLOYDatabase

AI chip · Huawei

Huawei Ascend 910B

Huawei's flagship domestic AI training accelerator, positioned as the primary Chinese alternative to Nvidia H100 after US export controls. Uses HBM3, Da Vinci architecture. Widely deployed at Chinese hyperscalers and government cloud regions.

On the DEPLOY graph: 2 robots on record adopt this chip · 1 campus carry a cited inventory line for it · 1 reference-design cluster include it.

Market position

The Chinese ceiling under US export controls. Fabbed at SMIC N+2 (~7 nm equivalent), sold into ByteDance, Baidu, iFlytek, Tencent and the domestic hyperscalers. 8,192-chip Atlas 900 A3 SuperCluster is the pod-scale endpoint. Ascend 910C/910D are the follow-ons.

DEPLOY editorial. What the vendor PDF cannot tell you.

Physical-AI cross-link

Derived from claims already on record (vendor first-party TDP, throughput, price, and the reference-design cluster registry). The arithmetic is shown per row so it can be audited. No estimated inputs.

Perf per watt
1.00 FP16 TFLOPS/W
400 TFLOPS ÷ 400 W = 1.00
Cooling class (across reference designs)
water
Observed across 1 reference-design cluster containing this chip

What fits in 64 GB

Weights-only footprint for public open-weight LLMs. Pure arithmetic: params × bytes/param. Excludes KV cache and activation memory; add ~10-30% headroom for real serving. A model that does not fit at FP16 may still fit at INT8 or INT4 with quality trade-offs. Not a benchmark.

ModelParamsFP16INT8INT4
Llama 3.1 8B
dense
8 B16 GB ✓8 GB ✓4 GB ✓
Llama 3.1 70B
dense
70 B140 GB ✗70 GB ✗35 GB ✓
Llama 3.1 405B
dense
405 B810 GB ✗405 GB ✗203 GB ✗
Llama 3.3 70B
dense
70 B140 GB ✗70 GB ✗35 GB ✓
DeepSeek V3
MoE (671B total, 37B active per token)
671 B1342 GB ✗671 GB ✗336 GB ✗
DeepSeek R1
MoE (671B total, 37B active per token)
671 B1342 GB ✗671 GB ✗336 GB ✗
Qwen 2.5 7B
dense
7 B14 GB ✓7 GB ✓4 GB ✓
Qwen 2.5 72B
dense
72 B144 GB ✗72 GB ✗36 GB ✓
Mixtral 8x7B
MoE (46.7B total, 12.9B active per token)
46.7 B93 GB ✗47 GB ✓23 GB ✓
Mixtral 8x22B
MoE (141B total, 39B active per token)
141 B282 GB ✗141 GB ✗71 GB ✗
Gemma 2 27B
dense
27 B54 GB ✓27 GB ✓14 GB ✓
Command R+
dense
104 B208 GB ✗104 GB ✗52 GB ✓
Kimi K2
MoE (1T total, 32B active per token)
1000 B2000 GB ✗1000 GB ✗500 GB ✗

Math: FP16 = params × 2 bytes; INT8 = params × 1 byte; INT4 = params × 0.5 bytes. MoE models sum every expert (full weights on disk), not the per-token active subset.

Common questions

Answer-first, sourced. Every claim below traces to a specific field on this page or a cited datasheet. FAQPage schema is emitted so LLM crawlers can lift these verbatim.

How much does Huawei Ascend 910B cost?

Huawei Ascend 910B launch pricing is not on record in the DEPLOY registry. Vendor list prices are typically published in the vendor's own briefing rather than the datasheet.

How much memory does Huawei Ascend 910B have?

64 GB of HBM2e at 1,600 GB/s. Vendor datasheet, first-party.

How much power does one Huawei Ascend 910B draw?

400 W TDP (thermal design power) per chip. System-level draw is higher: see the reference-design section for rack-level kW.

What runs on Huawei Ascend 910B?

2 robot models on the DEPLOY registry adopt this chip, including AgiBot A2, AgiBot Yuanzheng A2. Full list below.

Which data centers have Huawei Ascend 910B?

1 campus on the DEPLOY registry carry a cited inventory line for this chip. Full list below with per-campus quantity hints where published.

Which open-weight LLMs fit on one Huawei Ascend 910B?

Of the 13 public open-weight LLMs DEPLOY tracks: 3 fit at FP16, 4 at INT8, 8 at INT4 (weights only, excludes KV cache). The full table is above with per-model math. Sparsity, offloading and multi-GPU serving change the picture; this row is single-chip weights-only.

Key facts

Class
Compute SoC (AI accelerator)
Designer
Huawei
Safety-critical?
No (data-center inference / training)
Record as of
2026-08-25
Latest cited claim
2024-06-01 (across 2 inventory + benchmark rows)
Specifications (9 fields, click to expand)

Vendor datasheet figures (first-party). Dense throughput first; sparse (2:4) in parentheses where NVIDIA quotes it. The exhaustive spec sheet lives on the datasheet URL below the table: this row set covers what buyers actually compare on.

Process node
SMIC N+2 (~7nm)
TDP
400 W
Memory
64 GB HBM2e
Memory bandwidth
1,600 GB/s
FP16 (dense)
400 TFLOPS
INT8 (dense)
800 TOPS
Form factor
OAM (Atlas 300T A2)
Announced
2023-08-01
Released
2023-08-01

Source: vendor datasheet

Generation

Used in reference designs

The named rack-scale and pod-scale designs buyers actually order that contain this chip.

See all reference designs →

Compare with

See every chip comparison →

Benchmarks

Published measurements per workload. Vendor datasheet numbers are first-party (verified posture); MLPerf / InferenceX / press results come in when their license terms + workload naming permit.

WorkloadValueUnitSourceAs of
peak tflops fp16(Reported spec from Huawei product materials)320TFLOPSvendor2023-08-01

Robot models running Huawei Ascend 910B

Every model on the DEPLOY registry with a public chip-integration claim for Huawei Ascend 910B. Ranked by verified deployment count.

ModelMakerForm factorRoleSourceDeployments
AgiBot A2AgiBothumanoidonboard humanoid compute (China stack)inferred3
AgiBot Yuanzheng A2AgiBothumanoidonboard humanoid compute (China stack)inferred1

Data centers stocking Huawei Ascend 910B

Who has the most? →

Every campus on the DEPLOY registry with a public claim of Huawei Ascend 910B on site. Quantity hints are unstructured because underlying disclosures vary by order of magnitude.

  1. Envision Galaxy Campusas of 2024-06-01
    partially energizedinferred

    Huawei Ascend AI capacity at the 1.5 GW Envision Ulanqab wind-fed AI factory

    Chinese AI campuses under export controls default to Huawei Ascend + domestic silicon.

    Envision Group

Sources

Adoption rows appear as we verify chip-integration claims per model. Every row is a public claim the maker or a tier-1 source has stated; verification tier (verified / reported / inferred) is shown per row. See every chip on record for the full catalog or the Huawei record.