AI chip · Intel Corporation
Intel Gaudi 2
Second-generation Habana Gaudi AI training accelerator, positioned as Intel's Nvidia H100 alternative before Gaudi 3. Powers Intel Developer Cloud AI instances.
Market position
Intel Habana's second-generation training chip. Shipped through Supermicro and Intel Developer Cloud. MLPerf training results were competitive with A100 through 2023. Superseded by Gaudi 3.
Efficiency and power
How much work you get per watt and per dollar, and how much power a full rack draws.
- Perf per watt
- 0.72 BF16 TFLOPS/W432 TFLOPS ÷ 600 W = 0.72
What fits in 96 GB
Which open-source LLMs run on one Intel Gaudi 2, 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 Intel Gaudi 2 cost?
Intel Gaudi 2 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 Intel Gaudi 2 have?
96 GB of HBM2e, running at 2,450 GB/s. Straight from the vendor datasheet. See chips with the most memory for context.
How much power does one Intel Gaudi 2 draw?
600 W at the chip. A full server draws more once you add CPU, memory, networking and cooling: see the rack power number above. Compare to other chips on perf-per-watt.
Which open-source LLMs fit on one Intel Gaudi 2?
Of 13 open-source LLMs we track, 4 fit at FP16, 7 at INT8, and 9 at INT4 (for example Llama 3.1 8B, Llama 3.1 70B and Llama 3.3 70B). Full table above with each model's memory need.
Key facts
- Class
- Compute SoC (AI accelerator)
- Designer
- Intel Corporation
- Safety-critical?
- No (data-center inference / training)
- Record as of
- 2026-09-27
Specifications (8 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
- TSMC N7
- TDP
- 600 W
- Memory
- 96 GB HBM2e
- Memory bandwidth
- 2,450 GB/s
- BF16 (dense)
- 432 TFLOPS
- Form factor
- OAM
- Announced
- 2022-05-10
- Released
- 2022-09-01
Source: vendor datasheet
Generation
Foundry & process
- Fabbed at
- TSMC (all chips TSMC makes →)
- Process node
- TSMC N7
Compare with
Sources
- Intel Gaudi 2Intel
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 Intel Corporation page.