Qwen / text-generation Open weights Also via API updated 1 year ago

Qwen2.5-72B-Instruct

Name: Qwen2.5-72B-Instruct
Price: 0.36 USD
Author: Qwen

Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2:

Params

72.7 B

Context

32,768

Downloads 30d

167 K

Likes

1,044

Licence: other Not gated SAFETENSORS 1 languages View on Hugging Face ↗

Download history

daily snapshots · 106 days

▲ 118 K in the last 30 days (41.5%)

527 K167 K

Jul 28Sep 1Oct 6Nov 10

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	145.4 GB	171.4 GB	❌ Won’t fit
model.safetensors (bf16, full)	bf16 + 32K ctx	145.4 GB	204.1 GB	❌ Won’t fit

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/qwen2-5-72b-instruct
{
  "hf_id": "Qwen/Qwen2.5-72B-Instruct",
  "params_b": 72.71,
  "context_length": 32768,
  "license": { "id": "other", "commercial": "unknown" },
  "downloads_30d": 166748,
  "vram_estimates": [
    { "quant": "bf16", "gb": 171.4 }
  ],
  "updated_at": "2026-07-28T18:05:06Z"
}

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

Use via API

via OpenRouter · USD per 1M tokens · synced 2026-11-10

$0.36

input / 1M

$0.40

output / 1M

—

cached input / 1M

$0.76

1M in + 1M out

Context window: 32,768 tokens
Max output: 16,384 tokens
Providers: 1
Cheapest provider: DeepInfra · $0.36 / $0.40
Best throughput: —
AA Intelligence / Coding / Agentic: — / — / —

✓ Tool calling ✗ Reasoning ✓ Structured outputs ✗ Image input ✗ File input ✗ Audio input ✗ Prompt caching

Specifications

Architecture: Qwen2ForCausalLM
Parameters: 72.7 B
Tensor type: BF16
Context length: 32,768
Vocabulary: 152,064
Layers / heads: 80 / 64
Licence: other
First seen on the Hub: 2024-09-16
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Family

Base model and the most-downloaded derivatives in the catalog.

Derivative Qwen2.5-72B-Instruct-AWQ Qwen 252 K

Compare with any text-generation model

Popular comparisons

dolphin-2.9.1-yi-1.5-34b 4.8 M Gemma-4-31B-IT-NVFP4 1.1 M Qwen2.5-Coder-32B-Instruct-AWQ 972 K Qwen3-32B-AWQ 222 K Llama-3.1-70B-Instruct 203 K Qwen3-Coder-Next-FP8-dynamic 170 K