Llama 2
Open-Weight LLM with Commercial License
Meta's second open-weight foundation model, released alongside a commercial-use license. The 70B variant approached GPT-3.5 on most benchmarks; the 7B and 13B variants made high-quality LLMs runnable on consumer hardware. Triggered the explosion of open-source LLM fine-tunes (Mistral, Vicuna v2, Code Llama, Llama 2 Chat clones).
Intelligence
Below avg
Speed
Medium
119 tok/s output
Cost
Low
$0.05 in / $0.25 out
Context
4K
Up to 4,096 tokens
How are Intelligence, Speed & Cost bucketed?
Intelligence and Speed buckets are percentile ranks on
Artificial Analysis. Cost buckets are fixed dollar
thresholds keyed off output-token price ($/M out).
Intelligence
- Top 1%≤ 1%
- Top 5%≤ 5%
- Top 10%≤ 10%
- Good≤ 25%
- Medium≤ 50%
- Below avg> 50%
Speed
- Top 1%≥ 345 tok/s
- Top 5%≥ 237 tok/s
- Top 10%≥ 196 tok/s
- Good≥ 146 tok/s
- Medium≥ 90 tok/s
- Slow< 90 tok/s
Cost
- Freeopen weights · self-host
- Low< $1 / M out
- Moderate$1–5 / M out
- High≥ $5 / M out
Why it matters
Llama 2 is when "open source AI" stopped being a research curiosity and started being a business model. The 2024-25 commodification of LLM inference pricing (per-million-tokens dropping >90% in 18 months) is a direct downstream effect.
Core Capabilities
Long Documents
Handles entire codebases, books, and multi-doc RAG.
Generative
Produces images, video, audio, or other media.
Context Window
4k tokens
≈ short doc
4k This model 本模型
32k Long docs 长文档
128k Books 整本书
400k Multi-doc 多文档
1M Codebase 整个代码库
10M
Availability
API
Not available
Product / App
Not available
Open Source
Released
Enterprise
—
Pricing Model
Free / self-host
Open weights — pay only for compute.
Self-host Capability / Performance
Where this model sits relative to the middle 60% of models in the tree. All scores are 0–10 (higher is better).
Lower 20% Upper 80% This model
Context / memory
Context window size · log-scaled
6.0
9.0
1.0
Lower 20% 20th percentile — 20% of models score below this This model Where the current model lands Upper 80% 80th percentile — only 20% of models score above this
Percentile boundaries are computed across every model in the tree that reports the underlying benchmark for each capability.
What it feels like
- Llama 2 era — historical baseline; superseded by Llama 3+.
- Major leap over Llama 2 — 70B operates in the same 'weight class' as GPT-4 and Claude 3 Sonnet at release
- Climbed to 5th place on the LMSYS leaderboard within weeks — first open-weights model to genuinely compete with GPT-4
- 128K-token vocabulary tokenizer noticeably improved encoding efficiency vs Llama 2
Best use cases
- Open-weights production deployments where Llama 2 was the previous baseline
- Self-hosted RAG, code-completion, and chat applications under Llama 3 license
- Fine-tuning on private corpora (the open license makes vertical specialisation safe)
Tools to try
Not ideal for
- Frontier reasoning leaderboards by late 2025 — superseded by Llama 3.1/3.3/4 and competitors
- Multimodal tasks — text-only at this generation (Llama 3.2 Vision came later)