Llama 3.3 70B
70 B parameters · 128K context · Llama 3.3 Community License · released 2024-12-06 by Meta.
Llama 3.3 70B needs about 140 GB at FP16: no single GPU can hold it. Serving requires an 8-GPU HGX baseboard (INT8/INT4) or a full rack (NVL72, TPU pod) at FP16.
Where this model sits
Meta's post-training refresh of the 70B: matches Llama 3.1 405B quality on many benchmarks at a fraction of the serving cost.
What runs it (production serving)
Datacenter GPUs and rack designs sized for Llama 3.3 70B. Consumer cards are not practical at this size.
Smallest datacenter GPU that fits (INT4)
Multi-GPU / rack-scale (FP16)
Memory at different context lengths
Weights are fixed. The KV cache grows linearly with context length and can rival the weights at full window. Most guides only quote weights, then hand-wave a 15% overhead, which is only true at short context.
| Context | FP16 total | INT8 total | INT4 total |
|---|---|---|---|
| 4K (short chat) | 140 + 1.3 = 141.3 GB | 70 + 0.6 = 70.6 GB | 35 + 0.6 = 35.6 GB |
| 32K (typical RAG) | 140 + 10.0 = 150.0 GB | 70 + 5.0 = 75.0 GB | 35 + 5.0 = 40.0 GB |
| 128K (full window) | 140 + 40.0 = 180.0 GB | 70 + 20.0 = 90.0 GB | 35 + 20.0 = 55.0 GB |
KV bytes per token = 2 × 80 layers × 8 KV heads × 128 head-dim × precision bytes. INT4 rows keep the KV cache at INT8 (typical serving default).
Quality benchmarks
Vendor-reported scores from the release blog or tech report. Every row cites its source.
| Benchmark | Score | Source | Date |
|---|---|---|---|
| MMLU (5-shot) | 86.0 | Meta Llama 3.3 model card | 2024-12-06 |
| HumanEval | 88.4 | Meta Llama 3.3 model card | 2024-12-06 |
| MATH (0-shot) | 77.0 | Meta Llama 3.3 model card | 2024-12-06 |
| GPQA | 50.5 | Meta Llama 3.3 model card | 2024-12-06 |
Speed and cost to serve
What cloud providers currently charge to serve Llama 3.3 70B. Tokens per second is what the provider publishes on their own page. Batch size, prompt length, and inference engine can shift these numbers a lot; treat as directional.
| Provider | Hardware | Speed | $/M in | $/M out | As of |
|---|---|---|---|---|---|
| Together AI Instruct Turbo | H100 | — | $0.88 | $0.88 | 2025-08-01 |
| Groq | Groq LPU | 250 tok/s | $0.59 | $0.79 | 2025-08-01 |
| Fireworks AI | — | — | $0.90 | $0.90 | 2025-08-01 |
Cheapest option in this list for output-heavy workloads: Groq at $0.79/M out. Fastest published: Groq at 250 tok/s (Groq LPU).
License and variants
- License
- Llama 3.3 Community License
- The gotcha
- 700M-MAU commercial threshold, same as prior Llama Community License.
- Variants
- Instruct
- Context window
- 131,072 tokens (128K)
- Architecture
- dense
Compare with
Model card: https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct · Release: Meta announcement
See also: every open-source LLM we track · all AI chips · rack designs.