tiiuae / text-generation updated 1 year ago

falcon-7b

Name: falcon-7b
Author: tiiuae

Falcon-7B is a 7B parameters causal decoder-only model built by TII and trained on 1,500B tokens of RefinedWeb enhanced with curated corpora. It is made available under the Apache 2.0 license.

Params

7.2 B

Context

—

Downloads 30d

1.2 M

Likes

1,104

Commercial use: allowed apache-2.0 Not gated SAFETENSORS 1 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days

1.2 M1.2 M

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	14.4 GB	17.5 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/falcon-7b
{
  "hf_id": "tiiuae/falcon-7b",
  "params_b": 7.22,
  "context_length": null,
  "license": { "id": "apache-2.0", "commercial": "yes" },
  "downloads_30d": 1183152,
  "vram_estimates": [
    { "quant": "bf16", "gb": 17.5 }
  ],
  "updated_at": "2026-07-28T18:03:30Z"
}

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

Specifications

Architecture: FalconForCausalLM
Parameters: 7.2 B
Tensor type: BF16
Vocabulary: 65,024
Layers / heads: 32 / 71
Licence: apache-2.0
First seen on the Hub: 2023-04-24
Training datasets: tiiuae/falcon-refinedweb
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