SELF-HOSTING # Kimi K2.7 Code: Self-Hosting Estimate Kimi K2.7 Code (Moonshot AI) on different GPUs: configuration, estimated performance and use cases. Data updated: 2026-09-16 [← All self-hosting estimates](https://www.tandiu.cn/en/local-deploy) Total parameters**1,027B**Sets weight VRAM Active parameters**32B**Sets decode compute and speed License**Modified MIT License**[Official repo →](https://huggingface.co/moonshotai/Kimi-K2.7-Code) Public benchmarks**AA — · LiveBench 0.0** Vendor API price**$0.95 / $4.00**input / output per 1M tokens · cached $0.190 · [Token prices →](https://www.tandiu.cn/en/token-market) 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 **INT8** GPUs needed **8priced as 1 × 8-GPU HGX node** Est. decode speed **2,000 tok/s**single-stream theoretical ceiling Est. batched throughput **out 3,400 tok/s**in 36,562 tok/s · many concurrent requests Hardware list price **$299,058–$498,429**Cloud rental (live) ×8: $63.08–$63.08/hr (2026-11-04) Hardware market price **$1,047,167** 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 **INT8** GPUs needed **8** Est. decode speed **2,000 tok/s**single-stream theoretical ceiling Est. batched throughput **out 3,400 tok/s**in 40,625 tok/s · many concurrent requests Hardware list price **$239,544–$359,316** Hardware market price **$718,058–$1,436,115** 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 **INT8** GPUs needed **8priced as 1 × 8-GPU HGX node** Est. decode speed **2,000 tok/s**single-stream theoretical ceiling Est. batched throughput **out 3,400 tok/s**in 36,562 tok/s · many concurrent requests Hardware list price **$299,058–$498,429**Cloud rental (live) ×8: $59.58–$100.08/hr (2026-11-05) Hardware market price **$448,786–$523,584** 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 **INT4 (AWQ/GPTQ)** GPUs needed **8priced as 1 × 8-GPU HGX node** Est. decode speed **2,400 tok/s**single-stream theoretical ceiling Est. batched throughput **out 4,080 tok/s**in 16,071 tok/s · many concurrent requests Hardware list price **$279,837–$499,708**Cloud rental (live) ×8: $23.93–$36.86/hr (2026-11-05) Hardware market price **$224,393–$233,369** 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 **INT4 (AWQ/GPTQ)** GPUs needed **8priced as 1 × 8-GPU HGX node** Est. decode speed **1,675 tok/s**single-stream theoretical ceiling Est. batched throughput **out 2,848 tok/s**in 16,071 tok/s · many concurrent requests Hardware list price **$239,860–$831,514**Cloud rental (live) ×8: $15.47–$32.90/hr (2026-11-05) Hardware market price **$320,732** 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 **INT4 (AWQ/GPTQ)** GPUs needed **8priced as 1 × 8-GPU HGX node** Est. decode speed **1,675 tok/s**single-stream theoretical ceiling Est. batched throughput **out 2,848 tok/s**in 16,071 tok/s · many concurrent requests Hardware list price **$293,207–$311,158** Hardware market price **$403,907–$418,867** 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 **INT4 (AWQ/GPTQ)** GPUs needed **8** Est. decode speed **2,000 tok/s**single-stream theoretical ceiling Est. batched throughput **out 3,400 tok/s**in 2,405 tok/s · many concurrent requests Hardware list price **n/a** Hardware market price **$95,741–$131,644** 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 **INT4 (AWQ/GPTQ)** GPUs needed **8** Est. decode speed **968 tok/s**single-stream theoretical ceiling Est. batched throughput **out 987 tok/s**in 3,042 tok/s · many concurrent requests · PCIe multi-GPU penalty Hardware list price **$119,676–$124,463** Hardware market price **$129,250–$143,612** Typical use Medium-scale inference/training deployment in export-compliant environments ## Ascend 910C 128GB 128 GB · 3,200 GB/s · Huawei dual-chip data center card (domestically produced) Suggested precision **INT4 (AWQ/GPTQ)** GPUs needed **8** Est. decode speed **1,600 tok/s**single-stream theoretical ceiling Est. batched throughput **out 2,720 tok/s**in 12,220 tok/s · many concurrent requests Hardware list price **n/a** Hardware market price **$95,741–$239,353** 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 **INT4 (AWQ/GPTQ)** GPUs needed **16 (exceeds one node: multi-node needed)** Est. decode speed **400 tok/s**single-stream theoretical ceiling Est. batched throughput **out 680 tok/s**in 10,400 tok/s · many concurrent requests Hardware list price **n/a** Hardware market price **$263,288–$287,223** 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 **INT4 (AWQ/GPTQ)** GPUs needed **8** Est. decode speed **896 tok/s**single-stream theoretical ceiling Est. batched throughput **out 914 tok/s**in 4,875 tok/s · many concurrent requests · PCIe multi-GPU penalty Hardware list price **$128,200**Cloud rental (live) ×8: $9.62–$18.15/hr (2026-11-05) Hardware market price **$140,691** 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 **INT4 (AWQ/GPTQ)** GPUs needed **8** Est. decode speed **699 tok/s**single-stream theoretical ceiling Est. batched throughput **out 713 tok/s**in 4,407 tok/s · many concurrent requests · PCIe multi-GPU penalty Hardware list price **$91,147** Hardware market price **$101,725–$107,709** 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 **INT4 (AWQ/GPTQ)** GPUs needed **16 (exceeds one node: multi-node needed)** Est. decode speed **1,344 tok/s**single-stream theoretical ceiling Est. batched throughput **out 1,371 tok/s**in 5,031 tok/s · many concurrent requests · PCIe multi-GPU penalty Hardware list price **n/a**Cloud rental (live) ×16: $8.98–$17.10/hr (2026-11-05) Hardware market price **$129,250** 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 **INT4 (AWQ/GPTQ)** GPUs needed **16 (exceeds one node: multi-node needed)** Est. decode speed **864 tok/s**single-stream theoretical ceiling Est. batched throughput **out 881 tok/s**in 7,059 tok/s · many concurrent requests · PCIe multi-GPU penalty Hardware list price **$107,709–$155,579**Cloud rental (live) ×16: $9.62–$14.59/hr (2026-11-05) Hardware market price **$107,709–$155,579** Typical use SME teams building inference services, medium-low concurrency ## L20 48GB 48 GB · 864 GB/s · Compliant inference card Suggested precision **INT4 (AWQ/GPTQ)** GPUs needed **16 (exceeds one node: multi-node needed)** Est. decode speed **864 tok/s**single-stream theoretical ceiling Est. batched throughput **out 881 tok/s**in 2,330 tok/s · many concurrent requests · PCIe multi-GPU penalty Hardware list price **$55,882–$56,202** Hardware market price **$83,773** 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 **INT4 (AWQ/GPTQ)** GPUs needed **32 (exceeds one node: multi-node needed)** Est. decode speed **3,584 tok/s**single-stream theoretical ceiling Est. batched throughput **out 3,656 tok/s**in 16,341 tok/s · many concurrent requests · PCIe multi-GPU penalty Hardware list price **n/a**Cloud rental (live) ×32: $14.14–$17.02/hr (2026-11-05) Hardware market price **$215,413** 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 **INT4 (AWQ/GPTQ)** GPUs needed **32 (exceeds one node: multi-node needed)** Est. decode speed **2,688 tok/s**single-stream theoretical ceiling Est. batched throughput **out 2,742 tok/s**in 11,583 tok/s · many concurrent requests · PCIe multi-GPU penalty Hardware list price **$78,982**Cloud rental (live) ×32: $14.14–$16.96/hr (2026-11-05) Hardware market price **$134,037–$191,482** 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 **INT4 (AWQ/GPTQ)** GPUs needed **32 (exceeds one node: multi-node needed)** Est. decode speed **2,016 tok/s**single-stream theoretical ceiling Est. batched throughput **out 2,056 tok/s**in 11,466 tok/s · many concurrent requests · PCIe multi-GPU penalty Hardware list price **$62,227–$90,949**Cloud rental (live) ×32: $10.82–$13.95/hr (2026-11-05) Hardware market price **$124,463–$143,612** 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.