Qwen / text-generation updated 1 year ago

Qwen2.5-7B-Instruct-1M

Qwen2.5-1M is the long-context version of the Qwen2.5 series models, supporting a context length of up to 1M tokens. Compared to the Qwen2.5 128K version, Qwen2.5-1M demonstrates significantly improved performance in handling long-context tasks while maintaining its capability in short tasks.

Params
7.6 B
Context
1,010,000
Downloads 30d
197 K
Likes
381
Commercial use: allowed apache-2.0 Not gated SAFETENSORS 1 languages View on Hugging Face ↗

Download history

daily snapshots · 24 days
230 K173 K
Aug 29Sep 6Sep 14Sep 21

Can you run it?

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

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
model.safetensors bf16 15.2 GB 18.4 GB ✅ Runs comfortably
model.safetensors (bf16, full) bf16 + 986K ctx 15.2 GB 158.2 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/qwen2-5-7b-instruct-1m
{
  "hf_id": "Qwen/Qwen2.5-7B-Instruct-1M",
  "params_b": 7.62,
  "context_length": 1010000,
  "license": { "id": "apache-2.0", "commercial": "yes" },
  "downloads_30d": 197266,
  "vram_estimates": [
    { "quant": "bf16", "gb": 18.4 }
  ],
  "updated_at": "2026-08-29T01:00:29Z"
}
est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture
Qwen2ForCausalLM
Parameters
7.6 B
Tensor type
BF16
Context length
1,010,000
Vocabulary
152,064
Layers / heads
28 / 28
Licence
apache-2.0
First seen on the Hub
2025-01-23
Base model
Qwen2.5-7B
Training datasets
undisclosed
Added to our catalog
2026-08-29

Family

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

Compare with any text-generation model