AI chip · AMD
AMD Instinct MI400
Announced June 2025 (ships 2026): AMD's CDNA 5 next generation. 432 GB HBM4 at 19.6 TB/s, 40 PFLOPS FP4 / 20 PFLOPS FP8. Anchors the Helios rack, AMD's answer to NVIDIA Vera Rubin.
Market position
Announced June 2025 (ships 2026): AMD's CDNA 5 next-gen. 432 GB HBM4 at 19.6 TB/s, 40 PFLOPS FP4 / 20 PFLOPS FP8, with a 300 GB/s scale-out link. Anchors the Helios rack (AMD's answer to NVIDIA Vera Rubin); the series includes MI455X (training/cloud) and MI430X (HPC). Specs provisional pending launch.
What fits in 432 GB
Which open-source LLMs run on one AMD Instinct MI400, by precision. Weights only: add roughly 15% headroom for real serving. If a model does not fit at FP16, try INT8 or INT4 (smaller quality trade-off than most people expect).
| Model | Params | FP16 | INT8 | INT4 |
|---|---|---|---|---|
| Llama 3.1 8B dense | 8 B | 16 GB ✓ | 8 GB ✓ | 4 GB ✓ |
| Llama 3.1 70B dense | 70 B | 140 GB ✓ | 70 GB ✓ | 35 GB ✓ |
| Llama 3.1 405B dense | 405 B | 810 GB ✗ | 405 GB ✓ | 203 GB ✓ |
| Llama 3.3 70B dense | 70 B | 140 GB ✓ | 70 GB ✓ | 35 GB ✓ |
| DeepSeek V3 MoE (671B total, 37B active per token) | 671 B | 1342 GB ✗ | 671 GB ✗ | 336 GB ✓ |
| DeepSeek R1 MoE (671B total, 37B active per token) | 671 B | 1342 GB ✗ | 671 GB ✗ | 336 GB ✓ |
| Qwen 2.5 7B dense | 7 B | 14 GB ✓ | 7 GB ✓ | 4 GB ✓ |
| Qwen 2.5 72B dense | 72 B | 144 GB ✓ | 72 GB ✓ | 36 GB ✓ |
| Mixtral 8x7B MoE (46.7B total, 12.9B active per token) | 46.7 B | 93 GB ✓ | 47 GB ✓ | 23 GB ✓ |
| Mixtral 8x22B MoE (141B total, 39B active per token) | 141 B | 282 GB ✓ | 141 GB ✓ | 71 GB ✓ |
| Gemma 2 27B dense | 27 B | 54 GB ✓ | 27 GB ✓ | 14 GB ✓ |
| Command R+ dense | 104 B | 208 GB ✓ | 104 GB ✓ | 52 GB ✓ |
| Kimi K2 MoE (1T total, 32B active per token) | 1000 B | 2000 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
How much does AMD Instinct MI400 cost?
AMD Instinct MI400 doesn't have a public launch list price. Vendors like this one usually price through direct sales rather than a public sheet. See list price per TFLOP for chips that do publish.
How much memory does AMD Instinct MI400 have?
432 GB of HBM4, running at 19,600 GB/s. Straight from the vendor datasheet. See chips with the most memory for context.
Which open-source LLMs fit on one AMD Instinct MI400?
Of 13 open-source LLMs we track, 9 fit at FP16, 10 at INT8, and 12 at INT4 (for example Llama 3.1 8B, Llama 3.1 70B and Llama 3.1 405B). Full table above with each model's memory need.
Key facts
- Class
- Compute SoC (AI accelerator)
- Designer
- AMD
- Safety-critical?
- No (data-center inference / training)
- Record as of
- 2026-09-27
Specifications (7 fields, click to expand)
Straight from the vendor datasheet. Dense throughput shown first; sparse (2:4) numbers in parentheses where the vendor publishes them. Full datasheet linked below.
- Process node
- CDNA 5 (TSMC 3nm)
- Memory
- 432 GB HBM4
- Memory bandwidth
- 19,600 GB/s
- FP8 (dense)
- 20,000 TFLOPS
- FP4 (dense)
- 40,000 TFLOPS
- Announced
- 2025-06-12
- Released
- 2026-06-01
Source: vendor datasheet
Generation
Foundry & process
- Process node
- CDNA 5 (TSMC 3nm)
Sources
Adoption rows appear as we confirm each chip-in-robot pairing from a public source. See every chip we track for the full catalog or the AMD page.