Meta · open-weights

Llama 3.1-8B

Llama 3.1-8B is an open-weights language model from Meta, released July 23, 2024. It has 8B parameters (dense). On the Epoch Capabilities Index it scores 111.1, rank 202 of 256 rated models.

Check it against your own PC →

Lab

Can you run Llama 3.1-8B locally?

The smallest common GPU it runs on is 6 GB of VRAM (with 32 GB of RAM): Q6_K, split GPU / CPU, roughly 6 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	Runs, slowly	Q6_K (≈ lossless)	5.2 GB	4.2 GB	~6
8 GB VRAM	Runs on GPU	IQ4_XS (good)	7.1 GB	–	~37
12 GB VRAM	Runs on GPU	Q6_K (≈ lossless)	9.4 GB	–	~32
16 GB VRAM	Runs on GPU	Q6_K (≈ lossless)	9.4 GB	–	~44
24 GB VRAM	Runs on GPU	Q6_K (≈ lossless)	9.4 GB	–	~79
32 GB VRAM	Runs on GPU	Q6_K (≈ lossless)	9.4 GB	–	~140

Ready-made quantizations on Hugging Face: NousResearch/Hermes-3-Llama-3.1-8B-GGUF · dphn/Dolphin3.0-Llama3.1-8B-GGUF · dphn/dolphin-2.9.4-llama3.1-8b-gguf · Mungert/UserLM-8b-GGUF · NousResearch/DeepHermes-3-Llama-3-8B-Preview-GGUF · Gurubot/self-after-dark

Strengths by category

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

Category	Score	Based on
Math	9.6	MATH level 5, OTIS Mock AIME 2024-2025
Knowledge	17.2	GPQA diamond, MMLU

Benchmark results

Benchmark (Epoch AI)	Score
MMLU	41.5%
MATH level 5	22.9%
Balrog	15.1%
GPQA Diamond	2.7%
OTIS Mock AIME	1.6%

Links

Hugging Face: meta-llama/Llama-3.1-8B · Epoch AI benchmarks

Models with a similar score

phi-3-medium 14B · Claude Instant · PaLM 2-L · Qwen2.5-Coder-14B · Mistral NeMo · Mixtral 8x7B · GPT-3.5 Turbo (Jan 2024) · GPT-3.5 Turbo (Nov 2023)