Meta · open-weights

Llama 2-70B

Llama 2-70B is an open-weights language model from Meta, released July 18, 2023. It has 70B parameters (dense). On the Epoch Capabilities Index it scores 105.8, rank 209 of 256 rated models.

Check it against your own PC →

Lab

Can you run Llama 2-70B locally?

The smallest common GPU it runs on is 24 GB of VRAM (with 32 GB of RAM): IQ2_XXS, fully on GPU, roughly 30 tokens per second. Estimates assume 32 GB of DDR5 RAM, a 16K context and llama.cpp-style GGUF quantization. Enter your exact hardware in the live app.

GPU memory	Verdict	Best quant	VRAM	RAM	tok/s
6 GB VRAM	Very slow	IQ2_XXS (heavy loss)	5.2 GB	17.8 GB	~2
8 GB VRAM	Very slow	IQ2_XXS (heavy loss)	7.2 GB	15.8 GB	~2
12 GB VRAM	Very slow	IQ2_XXS (heavy loss)	11.2 GB	11.8 GB	~2
16 GB VRAM	Very slow	IQ2_XXS (heavy loss)	15.2 GB	7.8 GB	~3
24 GB VRAM	Runs on GPU	IQ2_XXS (heavy loss)	23.0 GB	–	~30
32 GB VRAM	Runs on GPU	IQ2_M (heavy loss)	28.6 GB	–	~44

Strengths by category

ModelTape's 0–100 fit on Epoch AI benchmark results.

Category	Score	Based on
Math	7.6	MATH level 5, OTIS Mock AIME 2024-2025
Knowledge	23.8	GPQA diamond, MMLU

Benchmark results

Benchmark (Epoch AI)	Score
MMLU	59.9%
MATH level 5	3.3%
GPQA Diamond	1.8%
OTIS Mock AIME	0.0%

Links

Epoch AI benchmarks

Models with a similar score

Stable Beluga 2 · Llama 3-8B · Qwen2.5-Coder (7B) · Falcon-180B · GPT-3.5 Turbo (Jun 2023) · Gemma 7B · Mistral 7B v0.1 · Yi-9B