🇺🇸 United States generalistReleased November 2024
Llama 3.3 70B
Meta
Open-sourceSelf-host
Verdict
A solid pick for self-hosting and full data control.
Skill profile
Not disclosed
Strengths
- Open-source and self-hostable
Limitations
- No native GDPR guarantee
- API pricing not disclosed
Who is it for
A good fit if…
- you want to control cost or self-host
Skip it if…
- you handle sensitive EU data
Access & availability
Self-hostable (open weights)
Key specifications
Context
128K
Input price
—
Output price
—
Speed
—
Price not auditedBenchmarks not audited
Privacy
Not GDPR-compliant
Run it locally
Workstation (64GB+)785k3k
| Quantization | Disk | RAM / VRAM | Typical hardware |
|---|---|---|---|
| Q4 · recommended | 40.2 GB | 46 GB | 64GB Mac / dual 24GB GPUs |
| Q8 · balanced | 75.5 GB | 85 GB | 96-128GB Mac Studio / 4× GPUs |
| FP16 · max quality | 141.2 GB | 157 GB | Server GPU infra (H100/A100…) |
Estimates for a moderate context. Long contexts need more RAM (KV cache).
🤗 Hugging Face
ollama run llama3.3:70b
Advanced data · for expertsArchitecture, modalities, detailed cost, full benchmarks▾
Advanced data · for experts
Architecture, modalities, detailed cost, full benchmarks
Architecture
—
Size
70.6B
Cutoff date
—
Inputs
text
Outputs
text
License
llama3.3
Hosting
—
Hallucination score
—
Estimated cost (API)
Typical exchange (~3k in / 1k out)
Not disclosed
1M in + 1M out
Not disclosed
All benchmarks
| Arena Elo | — |
| MMLU | — |
| GPQA | — |
| HumanEval | — |
| SWE-Bench | — |
| MATH | — |