Llama 3.3
Llama-3.3-70B-Instruct
Meta AI · open-restricted llama3.3
| Parameters (B) | 70.554 |
|---|---|
| Architecture | dense |
| Layers / KV heads / head dim | 80 / 8 / 128 |
| Context window | 131072 |
| Modalities | in: text; out: text |
| GGUF | available |
| Commercial use | yes |
Minimum hardware (estimate)
At Q4_K_M and 8k context, total working set ≈ 46.1 GiB. On a machine with 64 GiB system RAM and no discrete GPU: Won't run. Limiting factor: No GPU and system RAM insufficient for weights + KV.
Scores
| Benchmark | Value | Uncertainty | Run by | Source |
|---|---|---|---|---|
| GPQA Diamond | 47.4% | unknown | third-party | epoch-ai |
| MATH Level 5 | 41.6% | unknown | third-party | epoch-ai |
| OTIS Mock AIME 2024-2025 | 5.1% | unknown | third-party | epoch-ai |
Provenance
- identity, license, architecture, parameter count: https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct (retrieved 2026-08-10)
HF: meta-llama/Llama-3.3-70B-Instruct · snapshot 2026-08-10