Model
Model explorer

Code Llama 34B

OPEN
Meta · Code Llama family · released Aug 24, 2023

34B code flagship, no infilling; HumanEval 48.8% pass@1 (Python variant reaches 53.7%).

ReasoningCodingVisionFunction callingTool useAgentic
264.5
Elo · rank #352
Parameters
34B
Active params
34B (dense)
Context
16K tokens
Architecture
Dense transformer (decoder-only), no infilling
License
Llama 2 Community License
Languages
—
API price (in/out)
No hosted API
Modalities
text
Benchmark results
Bar shows position within the tracked field; marker = field best
GSM8KMath32.7%#149
best: Llama 3.1 405B · 96.8%
HumanEvalCoding48.8%#126
best: Claude Opus 4.5 · 99.4%
MBPPCoding55.0%#65
best: Llama-3.3-Nemotron-Super-49B v1 (Reasoning On) · 91.3%
RepoBenchCoding39.8%#2
best: DeepSeek Coder 33B · 41.9%
Run it locally
VRAM @ Q4
22 GB
VRAM @ FP16
68 GB
Fits on (Q4)
RTX 3090 24GBRTX 4090 24GBRTX 5090 32GBM4 Pro 48GBM3 Max 128GBM3 Ultra 512GBA100 80GBH100 80GBH200 141GBB200 192GB
Throughput data unavailable.
Quantizations
GGUF Q4 · GPTQ · AWQ · MLX
Code Llama family
Elo progression across releases
Code Llama 13BAug 2023232.3Code Llama 34BAug 2023264.5Code Llama 34B PythonAug 2023100.1Code Llama 7BAug 2023127.6Code Llama 70BJan 2024472.7Code Llama 70B InstructJan 2024618.8
Resources
HFmeta-llama/CodeLlama-34b-hfGHfacebookresearch/codellamaDOCSai.meta.com/blog/code-llama-large-language-model-codingAPIAvailable via Meta API
API price weights · each benchmark row carries its own source badge (see methodology)