AI chip · Meta
Meta MTIA v2
Second-generation MTIA, ~3x compute per package, doubled memory bandwidth. Announced April 2024.
On the DEPLOY graph: 2 campuses carry a cited inventory line for it.
Market position
Meta's second-generation in-house silicon for recommendation and ranking (news feed, Reels, ads). Not sold. Deployed at scale across every Meta AI campus (Prometheus, Hyperion) alongside NVIDIA. Signals Meta's long-term aim to reduce NVIDIA dependency for inference.
DEPLOY editorial. What the vendor PDF cannot tell you.
What fits in 128 GB
Weights-only footprint for public open-weight LLMs. Pure arithmetic: params × bytes/param. Excludes KV cache and activation memory; add ~10-30% headroom for real serving. A model that does not fit at FP16 may still fit at INT8 or INT4 with quality trade-offs. Not a benchmark.
| 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
Answer-first, sourced. Every claim below traces to a specific field on this page or a cited datasheet. FAQPage schema is emitted so LLM crawlers can lift these verbatim.
How much does Meta MTIA v2 cost?
Meta MTIA v2 launch pricing is not on record in the DEPLOY registry. Vendor list prices are typically published in the vendor's own briefing rather than the datasheet.
How much memory does Meta MTIA v2 have?
128 GB of LPDDR5 at 205 GB/s. Vendor datasheet, first-party.
How much power does one Meta MTIA v2 draw?
90 W TDP (thermal design power) per chip. System-level draw is higher: see the reference-design section for rack-level kW.
Which data centers have Meta MTIA v2?
2 campuses on the DEPLOY registry carry a cited inventory line for this chip. Full list below with per-campus quantity hints where published.
Which open-weight LLMs fit on one Meta MTIA v2?
Of the 13 public open-weight LLMs DEPLOY tracks: 4 fit at FP16, 8 at INT8, 9 at INT4 (weights only, excludes KV cache). The full table is above with per-model math. Sparsity, offloading and multi-GPU serving change the picture; this row is single-chip weights-only.
Key facts
- Class
- Compute SoC (AI accelerator)
- Designer
- Meta
- Safety-critical?
- No (data-center inference / training)
- Record as of
- 2026-08-25
- Latest cited claim
- 2024-04-10 (across 2 inventory + benchmark rows)
Specifications (8 fields, click to expand)
Vendor datasheet figures (first-party). Dense throughput first; sparse (2:4) in parentheses where NVIDIA quotes it. The exhaustive spec sheet lives on the datasheet URL below the table: this row set covers what buyers actually compare on.
- Process node
- TSMC N5
- TDP
- 90 W
- Memory
- 128 GB LPDDR5
- Memory bandwidth
- 205 GB/s
- INT8 (dense)
- 708 TOPS
- Form factor
- PCIe (internal Meta)
- Announced
- 2024-04-10
- Released
- 2024-05-01
Source: vendor datasheet
Generation
Compare with
Data centers stocking Meta MTIA v2
Who has the most? →Every campus on the DEPLOY registry with a public claim of Meta MTIA v2 on site. Quantity hints are unstructured because underlying disclosures vary by order of magnitude.
- Meta Hyperion Data Center (Richland Parish)as of 2024-04-10under constructionreported
Meta's own AI accelerator generation deployed at Hyperion
- Meta Prometheus Data Center (New Albany)as of 2024-04-10partially energizedreported
Meta's own AI accelerator generation deployed alongside Nvidia at Prometheus
Sources
- Next-generation Meta MTIAMeta AI
Adoption rows appear as we verify chip-integration claims per model. Every row is a public claim the maker or a tier-1 source has stated; verification tier (verified / reported / inferred) is shown per row. See every chip on record for the full catalog or the Meta record.