Model
Model explorer

LLaMA 13B

OPEN
Meta · LLaMA family · released Feb 24, 2023

LLaMA-1 13B; Meta reported it outperforming GPT-3 175B on most benchmarks despite being far smaller.

ReasoningCodingVisionFunction callingTool useAgentic
0.6
Elo · rank #402
Parameters
13B
Active params
13B (dense)
Context
2.048K tokens
Architecture
Dense decoder-only Transformer (RMSNorm, SwiGLU, rotary position embeddings)
License
LLaMA License (non-commercial research, gated/case-by-case access)
Languages
20+
API price (in/out)
No hosted API
Modalities
text
Benchmark results
Bar shows position within the tracked field; marker = field best
AGIEvalReasoning33.9%#34
best: OLMo 3-Think 32B · 88.2%
ARC-ChallengeReasoning52.7%#118
best: Llama 3.1 405B · 96.9%
ARC-EasyReasoning74.8%#37
best: Phi-3-medium (14B) · 97.7%
BIG-Bench HardReasoning37.0%#116
best: ERNIE 4.5 300B-A47B · 94.3%
GSM8KMath17.8%#166
best: Llama 3.1 405B · 96.8%
HellaSwagReasoning79.2%#88
best: Claude 3 Opus · 95.4%
HumanEvalCoding15.8%#175
best: Claude Opus 4.5 · 99.4%
MATH-500Math3.9%#199
best: GPT-5 · 99.4%
MBPPCoding22.0%#105
best: Llama-3.3-Nemotron-Super-49B v1 (Reasoning On) · 91.3%
MMLU (STEM)Knowledge35.8%#10
best: Falcon-H1 34B · 83.6%
MMLUKnowledge46.9%#240
best: OpenAI o3 · 92.9%
OpenBookQAReasoning56.4%#19
best: Claude 1 · 90.8%
PIQAReasoning80.1%#43
best: GPT-4o mini · 93.1%
RACE-HReasoning47.2%#15
best: Claude 3 Opus · 92.9%
Social IQaReasoning50.4%#25
best: Apple DCLM-Baseline 7B · 82.9%
TriviaQAKnowledge56.6%#37
best: Sarvam-1 (2B) · 90.6%
WinoGrandeReasoning73.0%#79
best: PaLM 2 · 90.9%
Run it locally
VRAM @ Q4
8 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
Original LLaMA-1 predates most public RTX 4090 llama.cpp benchmarks (which target Llama 2/3); no verified figure for this exact checkpoint was found.
Quantizations
GGUF Q4_K_M · GGML · GPTQ · AWQ
LLaMA family
Elo progression across releases
LLaMA 13BFeb 20230.6LLaMA 33BFeb 2023184.9LLaMA 65BFeb 2023240.9LLaMA 7BFeb 2023-180.9
Resources
HFhuggyllama/llama-13bGHfacebookresearch/llamaDOCSarxiv.org/abs/2302.13971
API price weights · each benchmark row carries its own source badge (see methodology)