钽TANDIU钽铥
SELF-HOSTING

Hunyuan A13B: Self-Hosting Estimate

Hunyuan A13B (Tencent) on different GPUs: configuration, estimated performance and use cases.

Data updated: 2026-09-16

← All self-hosting estimates

Total parameters80BSets weight VRAM
Active parameters13BSets decode compute and speed
Public benchmarksNo public benchmark yet
Vendor API output speed—measured by Artificial Analysis; compare with local estimates below

B300 288GB

288 GB · 8,000 GB/s · Top-tier Blackwell card (no official channels to China)
Suggested precision
FP16/BF16 (full precision)
GPUs needed
1priced as 1 × 8-GPU HGX node
Est. decode speed
308 tok/ssingle-stream theoretical ceiling
Est. batched throughput
out 523 tok/sin 11,250 tok/s · many concurrent requests
Hardware list price
$400,084–$440,093Cloud rental (live): $9.94–$12.50/hr (2026-11-20)
Hardware market price
$2,545,253–$2,994,415
Typical use
Enterprise-grade ultra-large-scale training and high-concurrency inference clusters

GB200 192GB (single card equivalent)

192 GB · 8,000 GB/s · Top-tier Blackwell card (no official channels to China)
Suggested precision
FP16/BF16 (full precision)
GPUs needed
1
Est. decode speed
308 tok/ssingle-stream theoretical ceiling
Est. batched throughput
out 523 tok/sin 12,500 tok/s · many concurrent requests
Hardware list price
$29,968–$44,952
Hardware market price
$89,832–$179,665
Typical use
Ultra-large-scale trillion-parameter model training and inference clusters (networked with Grace CPU)

B200 180GB

180 GB · 8,000 GB/s · Top-tier Blackwell card (no official channels to China)
Suggested precision
FP16/BF16 (full precision)
GPUs needed
2priced as 1 × 8-GPU HGX node
Est. decode speed
615 tok/ssingle-stream theoretical ceiling
Est. batched throughput
out 1,046 tok/sin 22,500 tok/s · many concurrent requests
Hardware list price
$360,075–$440,093Cloud rental (live) ×2: $16.55–$17.50/hr (2026-11-20)
Hardware market price
$449,162–$524,023
Typical use
Enterprise-grade large-scale online inference and training

H200 141GB

141 GB · 4,800 GB/s · Top-tier export-controlled card (channels to China are volatile)
Suggested precision
FP16/BF16 (full precision)
GPUs needed
2priced as 1 × 8-GPU HGX node
Est. decode speed
369 tok/ssingle-stream theoretical ceiling
Est. batched throughput
out 628 tok/sin 9,890 tok/s · many concurrent requests
Hardware list price
$248,053–$320,067Cloud rental (live) ×2: $7.48–$14.26/hr (2026-11-20)
Hardware market price
$1,003,129–$1,033,073
Typical use
Enterprise-grade production environment high-concurrency inference

H100 SXM5 80GB

80 GB · 3,350 GB/s · Top-tier export-controlled card (no official channels to China)
Suggested precision
FP16/BF16 (full precision)
GPUs needed
4priced as 1 × 8-GPU HGX node
Est. decode speed
515 tok/ssingle-stream theoretical ceiling
Est. batched throughput
out 876 tok/sin 19,780 tok/s · many concurrent requests
Hardware list price
$296,061–$309,064Cloud rental (live) ×4: $6.88–$17.43/hr (2026-11-20)
Hardware market price
$501,565
Typical use
Enterprise-grade production environment high-concurrency inference/training

H800 SXM 80GB

80 GB · 3,350 GB/s · Top-tier export-controlled card (discontinued)
Suggested precision
FP16/BF16 (full precision)
GPUs needed
4priced as 1 × 8-GPU HGX node
Est. decode speed
515 tok/ssingle-stream theoretical ceiling
Est. batched throughput
out 876 tok/sin 19,780 tok/s · many concurrent requests
Hardware list price
$293,453–$311,419
Hardware market price
$404,246–$419,218
Typical use
Enterprise-grade production deployment (original China-compliant model, now discontinued)

H20 96GB

96 GB · 4,000 GB/s · Export-compliant special supply card (significantly reduced compute power)
Suggested precision
FP16/BF16 (full precision)
GPUs needed
2
Est. decode speed
308 tok/ssingle-stream theoretical ceiling
Est. batched throughput
out 523 tok/sin 1,480 tok/s · many concurrent requests
Hardware list price
n/a
Hardware market price
$52,402
Typical use
Suboptimal choice in export-compliant environments, medium-to-large scale inference deployment (FP16 compute power is only about 15% of H100, but higher memory bandwidth offers an advantage in decode-intensive scenarios)

A800 PCIe 80GB

80 GB · 1,935 GB/s · Compliant special supply card (export compliance status adjusted multiple times)
Suggested precision
FP16/BF16 (full precision)
GPUs needed
4
Est. decode speed
298 tok/ssingle-stream theoretical ceiling
Est. batched throughput
out 304 tok/sin 3,744 tok/s · many concurrent requests · PCIe multi-GPU penalty
Hardware list price
$59,888–$62,284
Hardware market price
$79,053
Typical use
Medium-scale inference/training deployment in export-compliant environments

Ascend 950DT 144GB

144 GB · 4,000 GB/s · Huawei's new-generation SuperNode card (domestic, parameters and prices for reference only)
Suggested precision
FP16/BF16 (full precision)
GPUs needed
2
Est. decode speed
308 tok/ssingle-stream theoretical ceiling
Est. batched throughput
out 523 tok/sin 5,000 tok/s · many concurrent requests
Hardware list price
n/a
Hardware market price
$232,367
Typical use
Domestic large model inference SuperNode (64-card SuperPoD), report states inference performance is approx. 0.86x that of H200 at the same latency

Ascend 910C 128GB

128 GB · 3,200 GB/s · Huawei dual-chip data center card (domestically produced)
Suggested precision
FP16/BF16 (full precision)
GPUs needed
2
Est. decode speed
246 tok/ssingle-stream theoretical ceiling
Est. batched throughput
out 418 tok/sin 7,520 tok/s · many concurrent requests
Hardware list price
n/a
Hardware market price
$23,955–$59,888
Typical use
Domestically produced large model training and inference clusters, CloudMatrix and other super-node solutions

Ascend 910B 64GB

64 GB · 400 GB/s · Domestic alternative (not subject to US export controls)
Suggested precision
FP16/BF16 (full precision)
GPUs needed
4
Est. decode speed
62 tok/ssingle-stream theoretical ceiling
Est. batched throughput
out 105 tok/sin 6,400 tok/s · many concurrent requests
Hardware list price
n/a
Hardware market price
$65,877–$71,866
Typical use
Domestic alternative, not subject to US export controls, medium-to-large scale inference/training deployment, memory bandwidth significantly lower than NVIDIA cards of similar VRAM capacity

RTX PRO 6000 Blackwell 96GB

96 GB · 1,792 GB/s · Professional workstation/server card (China-specific version is 6000D 84GB)
Suggested precision
FP16/BF16 (full precision)
GPUs needed
2
Est. decode speed
138 tok/ssingle-stream theoretical ceiling
Est. batched throughput
out 141 tok/sin 3,000 tok/s · many concurrent requests · PCIe multi-GPU penalty
Hardware list price
$32,077Cloud rental (live) ×2: $2.64–$4.01/hr (2026-11-20)
Hardware market price
$50,905
Typical use
Single-card large VRAM inference, local deployment of medium MoE models, private all-in-one machine

RTX PRO 5500 Blackwell 84GB

84 GB · 1,398 GB/s · Professional workstation card (specs are NVIDIA preliminary data)
Suggested precision
FP16/BF16 (full precision)
GPUs needed
4
Est. decode speed
215 tok/ssingle-stream theoretical ceiling
Est. batched throughput
out 219 tok/sin 5,424 tok/s · many concurrent requests · PCIe multi-GPU penalty
Hardware list price
$45,612
Hardware market price
$50,905–$53,899
Typical use
Workstation large VRAM inference, departmental private deployment

RTX PRO 5000 Blackwell 48GB

48 GB · 1,344 GB/s · Professional workstation card
Suggested precision
FP16/BF16 (full precision)
GPUs needed
4
Est. decode speed
207 tok/ssingle-stream theoretical ceiling
Est. batched throughput
out 211 tok/sin 3,096 tok/s · many concurrent requests · PCIe multi-GPU penalty
Hardware list price
n/aCloud rental (live) ×4: $2.41–$4.54/hr (2026-11-20)
Hardware market price
$17,233
Typical use
Small to medium model inference, development testing, single-machine multi-card private deployment

L40S 48GB

48 GB · 864 GB/s · Compliant inference card
Suggested precision
FP16/BF16 (full precision)
GPUs needed
4
Est. decode speed
133 tok/ssingle-stream theoretical ceiling
Est. batched throughput
out 136 tok/sin 4,344 tok/s · many concurrent requests · PCIe multi-GPU penalty
Hardware list price
$26,950–$38,927Cloud rental (live) ×4: $1.87–$3.21/hr (2026-11-20)
Hardware market price
$26,950–$38,927
Typical use
SME teams building inference services, medium-low concurrency

L20 48GB

48 GB · 864 GB/s · Compliant inference card
Suggested precision
FP16/BF16 (full precision)
GPUs needed
4
Est. decode speed
133 tok/ssingle-stream theoretical ceiling
Est. batched throughput
out 136 tok/sin 1,434 tok/s · many concurrent requests · PCIe multi-GPU penalty
Hardware list price
$13,982–$14,062
Hardware market price
$20,961
Typical use
SME teams building inference services, medium-low concurrency

RTX 5090 32GB

32 GB · 1,792 GB/s · Consumer flagship (not sold in China, 5090D for domestic market)
Suggested precision
FP16/BF16 (full precision)
GPUs needed
8
Est. decode speed
551 tok/ssingle-stream theoretical ceiling
Est. batched throughput
out 562 tok/sin 10,056 tok/s · many concurrent requests · PCIe multi-GPU penalty
Hardware list price
$16,002Cloud rental (live) ×8: $3.65–$4.81/hr (2026-11-20)
Hardware market price
$57,493–$62,284
Typical use
Local inference and development for individuals/small teams, multi-card VRAM pooling for quantized MoE

RTX 5090D 24GB

24 GB · 1,344 GB/s · Consumer-grade/small-scale self-built
Suggested precision
FP16/BF16 (full precision)
GPUs needed
8
Est. decode speed
414 tok/ssingle-stream theoretical ceiling
Est. batched throughput
out 422 tok/sin 7,128 tok/s · many concurrent requests · PCIe multi-GPU penalty
Hardware list price
$19,762
Hardware market price
$33,537–$47,911
Typical use
Personal development/small-scale verification/POC, not recommended for production-level high concurrency

RTX 4090D 24GB

24 GB · 1,008 GB/s · Consumer-grade/small-scale self-built
Suggested precision
FP16/BF16 (full precision)
GPUs needed
8
Est. decode speed
310 tok/ssingle-stream theoretical ceiling
Est. batched throughput
out 316 tok/sin 7,056 tok/s · many concurrent requests · PCIe multi-GPU penalty
Hardware list price
$15,570
Hardware market price
$20,960
Typical use
Personal development/small-scale verification/POC, not recommended for production-level high concurrency
FAQ

FAQ

How is the estimated decode speed calculated?

Estimated speed = (memory bandwidth × GPU count) ÷ (active parameters × bytes per parameter): the memory-bound upper limit for one request (roofline). It scales linearly with GPU count and ignores interconnect overhead, batching and framework losses, so real results are usually well below it.

Can I trust the speed numbers for consumer GPUs?

The linear assumption is reasonable for NVLink data-center cards (H/B series) but too optimistic for consumer PCIe cards without NVLink (RTX 5090D/4090D); multi-GPU consumer setups lose far more to communication, so equal-looking numbers do not mean equal performance.

How is “Suggested precision” chosen?

It is the highest precision that fits within 8 GPUs; beyond that it is flagged as multi-node.

Where do the prices come from?

USD converted at ¥6.68 per USD. Cloud rental is the international vast.ai market rate, not a China purchase price.