SELF-HOSTING # MiniMax M3.1 Flash: Self-Hosting Estimate MiniMax M3.1 Flash (MiniMax) 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**220B**Sets weight VRAM Active parameters**23B**Sets decode compute and speed License**other**[Official repo →](https://huggingface.co/MiniMaxAI/MiniMax-M3.1-Flash) Public benchmarks**AA 42.7 · LiveBench 73.1** Vendor API price**$0.15 / $0.60**input / output per 1M tokens · cached $0.015 · [Token prices →](https://www.tandiu.cn/en/token-market) Vendor API output speed**92.5 tok/s**first token 1.51s · 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 **2priced as 1 × 8-GPU HGX node** Est. decode speed **348 tok/s**single-stream theoretical ceiling · vendor API 92 tok/s Est. batched throughput **out 591 tok/s**in 12,717 tok/s · many concurrent requests Hardware list price **$497,650**Cloud rental (live) ×2: $11.80–$19.88/hr (2026-10-23) Hardware market price **$1,047,669** 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 **4** Est. decode speed **696 tok/s**single-stream theoretical ceiling · vendor API 92 tok/s Est. batched throughput **out 1,183 tok/s**in 28,261 tok/s · many concurrent requests Hardware list price **$119,829–$179,744** Hardware market price **$359,201–$718,402** 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 **4priced as 1 × 8-GPU HGX node** Est. decode speed **696 tok/s**single-stream theoretical ceiling · vendor API 92 tok/s Est. batched throughput **out 1,183 tok/s**in 25,435 tok/s · many concurrent requests Hardware list price **$240,679–$563,744**Cloud rental (live) ×4: $25.01–$34.44/hr (2026-10-23) Hardware market price **$449,001–$523,834** 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 **4priced as 1 × 8-GPU HGX node** Est. decode speed **417 tok/s**single-stream theoretical ceiling · vendor API 92 tok/s Est. batched throughput **out 710 tok/s**in 11,180 tok/s · many concurrent requests Hardware list price **$248,505–$450,916**Cloud rental (live) ×4: $18.43–$18.43/hr (2026-10-23) Hardware market price **$224,500–$233,481** 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 **8priced as 1 × 8-GPU HGX node** Est. decode speed **583 tok/s**single-stream theoretical ceiling · vendor API 92 tok/s Est. batched throughput **out 990 tok/s**in 22,360 tok/s · many concurrent requests Hardware list price **$216,440–$833,693**Cloud rental (live) ×8: $19.21–$49.41/hr (2026-10-23) Hardware market price **$404,101–$419,068** 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 **8priced as 1 × 8-GPU HGX node** Est. decode speed **583 tok/s**single-stream theoretical ceiling · vendor API 92 tok/s Est. batched throughput **out 990 tok/s**in 22,360 tok/s · many concurrent requests Hardware list price **$293,347–$311,307** Hardware market price **$404,101–$419,068** 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 **8** Est. decode speed **696 tok/s**single-stream theoretical ceiling · vendor API 92 tok/s Est. batched throughput **out 1,183 tok/s**in 3,346 tok/s · many concurrent requests Hardware list price **n/a** Hardware market price **$95,787–$131,707** 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 **8** Est. decode speed **337 tok/s**single-stream theoretical ceiling · vendor API 92 tok/s Est. batched throughput **out 343 tok/s**in 4,232 tok/s · many concurrent requests · PCIe multi-GPU penalty Hardware list price **$119,734–$124,523** Hardware market price **$173,614** 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 **FP16/BF16 (full precision)** GPUs needed **8** Est. decode speed **557 tok/s**single-stream theoretical ceiling · vendor API 92 tok/s Est. batched throughput **out 946 tok/s**in 17,002 tok/s · many concurrent requests Hardware list price **n/a** Hardware market price **n/a** 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 **INT8** GPUs needed **8** Est. decode speed **139 tok/s**single-stream theoretical ceiling · vendor API 92 tok/s Est. batched throughput **out 237 tok/s**in 7,235 tok/s · many concurrent requests Hardware list price **n/a** Hardware market price **$131,707–$143,680** 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 **8** Est. decode speed **312 tok/s**single-stream theoretical ceiling · vendor API 92 tok/s Est. batched throughput **out 318 tok/s**in 6,783 tok/s · many concurrent requests · PCIe multi-GPU penalty Hardware list price **$128,261**Cloud rental (live) ×8: $10.26–$20.02/hr (2026-10-23) Hardware market price **n/a** 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 **8** Est. decode speed **243 tok/s**single-stream theoretical ceiling · vendor API 92 tok/s Est. batched throughput **out 248 tok/s**in 6,131 tok/s · many concurrent requests · PCIe multi-GPU penalty Hardware list price **n/a** Hardware market price **$101,774–$113,747** 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 **INT8** GPUs needed **8** Est. decode speed **467 tok/s**single-stream theoretical ceiling · vendor API 92 tok/s Est. batched throughput **out 477 tok/s**in 3,500 tok/s · many concurrent requests · PCIe multi-GPU penalty Hardware list price **n/a**Cloud rental (live) ×8: $5.35–$9.62/hr (2026-10-23) Hardware market price **$64,656** 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 **INT8** GPUs needed **8** Est. decode speed **301 tok/s**single-stream theoretical ceiling · vendor API 92 tok/s Est. batched throughput **out 307 tok/s**in 4,911 tok/s · many concurrent requests · PCIe multi-GPU penalty Hardware list price **$53,880–$77,827**Cloud rental (live) ×8: $3.75–$6.47/hr (2026-10-23) Hardware market price **$53,880–$77,827** Typical use SME teams building inference services, medium-low concurrency ## L20 48GB 48 GB · 864 GB/s · Compliant inference card Suggested precision **INT8** GPUs needed **8** Est. decode speed **301 tok/s**single-stream theoretical ceiling · vendor API 92 tok/s Est. batched throughput **out 307 tok/s**in 1,621 tok/s · many concurrent requests · PCIe multi-GPU penalty Hardware list price **$27,954–$28,115** Hardware market price **$29,933–$41,907** 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 **8** Est. decode speed **1,247 tok/s**single-stream theoretical ceiling · vendor API 92 tok/s Est. batched throughput **out 1,272 tok/s**in 5,684 tok/s · many concurrent requests · PCIe multi-GPU penalty Hardware list price **n/a**Cloud rental (live) ×8: $4.07–$6.75/hr (2026-10-23) Hardware market price **$41,907–$64,656** 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 **8** Est. decode speed **935 tok/s**single-stream theoretical ceiling · vendor API 92 tok/s Est. batched throughput **out 954 tok/s**in 4,029 tok/s · many concurrent requests · PCIe multi-GPU penalty Hardware list price **$19,755**Cloud rental (live) ×8: $4.18–$6.42/hr (2026-10-23) Hardware market price **$33,525–$47,893** 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 **8** Est. decode speed **701 tok/s**single-stream theoretical ceiling · vendor API 92 tok/s Est. batched throughput **out 715 tok/s**in 3,988 tok/s · many concurrent requests · PCIe multi-GPU penalty Hardware list price **$15,564–$22,748**Cloud rental (live) ×8: $3.29–$4.28/hr (2026-10-23) Hardware market price **$31,131–$35,920** 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.