Model

Llama 2 13B Chat

OPEN

Meta · Llama 2 family · released Jul 18, 2023

RLHF-tuned dialogue version of Llama 2 13B, fine-tuned with SFT plus human-preference RLHF for helpfulness and safety.

ReasoningCodingVisionFunction callingTool useAgentic

105.1

Elo · rank #382

Parameters

13B

Active params

13B (dense)

Context

4K tokens

Architecture

Dense decoder-only Transformer

License

Llama 2 Community License Agreement

Languages

—

API price (in/out)

No hosted API

Modalities

text

Benchmark results

Bar shows position within the tracked field; marker = field best

ARC-ChallengeReasoning51.4%#120

best: Llama 3.1 405B · 96.9%

BIG-Bench HardReasoning33.2%#123

best: ERNIE 4.5 300B-A47B · 94.3%

DROPReasoning23.87#63

best: Hunyuan-T1 · 93.1

GPQA DiamondReasoning20.2%#283

best: GPT-5.6 · 94.6%

GSM8KMath15.2%#171

best: Llama 3.1 405B · 96.8%

IFEvalReasoning34.0%#139

best: Gemma 4 26B A4B · 98.5%

MMLU (EU-21 languages)Knowledge42.9%#13

best: Llama 3.1 70B · 77.1%

MMLU-ProKnowledge19.2%#172

best: Claude Fable 5 · 91.5%

RakudaHuman preference2.27#6

best: PLaMo-100B · 9.73

TruthfulQAKnowledge62.2%#20

best: Phi-3.5-MoE (16x3.8B, 6.6B active) · 77.5%

WinoGrandeReasoning74.5%#71

best: PaLM 2 · 90.9%

Run it locally

VRAM @ Q4

10 GB

VRAM @ FP16

26 GB

Fits on (Q4)

RTX 3060 12GBRTX 4070 Ti 16GBRTX 3090 24GBRTX 4090 24GBRTX 5090 32GBM4 Pro 48GBM3 Max 128GBM3 Ultra 512GBA100 80GBH100 80GBH200 141GBB200 192GB

~70.9 tok/s on RTX 4090 (Q4, llama.cpp)

Quantizations

GGUF Q4 · GGUF · GPTQ · AWQ · GGML

Llama 2 family

Elo progression across releases

Llama 2 13BJul 202369.7 Llama 2 13B ChatJul 2023105.1 Llama 2 70BJul 2023365.0 Llama 2 70B ChatJul 2023363.8 Llama 2 7BJul 2023-121.8 Llama 2 7B ChatJul 2023-10.6

Resources

HFmeta-llama/Llama-2-13b-chat GHmeta-llama/llama DOCSai.meta.com/llama APIAvailable via Meta API

API price weights · each benchmark row carries its own source badge (see methodology)