Llama 3.1 8B

Name: Llama 3.1 8B
Rating: 69 (185 reviews)
Author: Meta

レガシー

HuggingFace

Ollama

10.5Mダウンロード5.9KいいねJul 2024公開日128K トークンコンテキストCommunityライセンス51 良好品質

Llama 3.1 8B (8B parameters) requires approximately 8.6 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 10 GB of VRAM.

はじめに

— コピー&ペーストでローカル実行

Copy-paste commands to run Llama 3.1 8B on your machine.

Run

ollama run llama3.1

Quick specs

Parameters8B

Architecturedense

Context128K tokens

Modalitytext

Min RAM3.1 GB

Rec. RAM4.9 GB (Q4_K_M)

LicenseCommunity

FamilyLlama

✓ Chat

About this model

Llama 3.1 8B is Meta's efficient general-purpose model supporting 128K context and multilingual text generation. Optimized for dialogue, summarization, reasoning, and code generation tasks.

Llama 3.1 8Bのおすすめ

このモデルを実行

Llama 3.1 8B on RTX 3080 Ti 12GB Llama 3.1 8B on RTX 5070 12GB Llama 3.1 8B on RTX 3080 12GB

量子化オプション

量子化レベル別VRAM推定値

No hardware detected — fit column shows raw VRAM estimates

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	3.1 GB	Low	—
Q3_K_S	3	3.9 GB	Low	—
NVFP4	4	4.5 GB	Medium	—
Q4_K_M	4	4.9 GB	Medium	—
Q5_K_M	5	5.8 GB	High	—
Q6_K	6	6.6 GB	High	—
Q8_0	8	8.6 GB	Very High	—
F16	16	16.4 GB	Maximum	—

Quality benchmarks

Llama 3.1 8B benchmark scores

Benchmark verified

Coding

SWE-bench Verified—

HumanEval+72.6%

Aider Polyglot—

LiveCodeBench—

Reasoning

MMLU-Pro48.3%

GPQA Diamond30.4%

MATH-50051.9%

ARC Challenge83.4%

General

Chatbot Arena—

IFEval80.4%

Source: official · 2024-07-23

ハードウェア互換性

全ハードウェアの適合度推定

カリキュレーターを開く

Computing compatibility...

メモリ内訳

Reference: RTX 2060 6GB

Weights4.9 GB

KV Cache2.0 GB

Runtime1.2 GB

Headroom0.6 GB

よくある質問

Llama 3.1 8B

Llama 3.1 8Bのおすすめ

量子化レベル別VRAM推定値

Llama 3.1 8B benchmark scores

全ハードウェアの適合度推定

Reference: RTX 2060 6GB

FAQ — Llama 3.1 8B