codellama / text-generation updated 2 years ago

CodeLlama-7b-hf

Name: CodeLlama-7b-hf
Author: codellama

Code Llama is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 34 billion parameters. This is the repository for the base 7B version in the Hugging Face Transformers format. This model is designed for general code synthesis and understanding. Links to other models can be found in the index at the bottom.

Params

6.7 B

Context

16,384

Downloads 30d

356 K

Likes

377

Commercial use: conditional · llama2 Not gated SAFETENSORS 1 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days

356 K238 K

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	bf16	13.5 GB	16.3 GB	✅ Runs comfortably
model.safetensors (bf16, full)	bf16 + 16K ctx	13.5 GB	17.3 GB	✅ Runs comfortably

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub

~ · curl · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/codellama-7b-hf
{
  "hf_id": "codellama/CodeLlama-7b-hf",
  "params_b": 6.74,
  "context_length": 16384,
  "license": { "id": "llama2", "commercial": "conditional" },
  "downloads_30d": 355998,
  "vram_estimates": [
    { "quant": "bf16", "gb": 16.3 }
  ],
  "updated_at": "2026-07-28T18:07:27Z"
}

est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture: LlamaForCausalLM
Parameters: 6.7 B
Tensor type: BF16
Context length: 16,384
Vocabulary: 32,016
Layers / heads: 32 / 32
Licence: llama2
First seen on the Hub: 2023-08-24
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Compare with

Qwen3-8B 16.3 M Qwen2.5-7B-Instruct 12.1 M Qwen3.6-35B-A3B-NVFP4 11.3 M Llama-3.1-8B-Instruct 8.0 M Qwen2.5-7B-Instruct-AWQ 4.6 M granite-4.1-8b 4.2 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB