Qwen / text-generation updated 2 years ago

Qwen1.5-MoE-A2.7B

Name: Qwen1.5-MoE-A2.7B
Author: Qwen

Qwen1.5-MoE is a transformer-based MoE decoder-only language model pretrained on a large amount of data.

Params

14.3 B

Context

8,192

Downloads 30d

198 K

Likes

228

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

Download history

daily snapshots · 10 days

214 K194 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	28.6 GB	34.1 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/qwen1-5-moe-a2-7b
{
  "hf_id": "Qwen/Qwen1.5-MoE-A2.7B",
  "params_b": 14.32,
  "context_length": 8192,
  "license": { "id": "other", "commercial": "unknown" },
  "downloads_30d": 197930,
  "vram_estimates": [
    { "quant": "bf16", "gb": 34.1 }
  ],
  "updated_at": "2026-07-28T18:07:50Z"
}

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

Specifications

Architecture: Qwen2MoeForCausalLM
Parameters: 14.3 B
Tensor type: BF16
Context length: 8,192
Vocabulary: 151,936
Layers / heads: 24 / 16
Licence: other
First seen on the Hub: 2024-02-29
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 gpt-oss-20b 8.6 M Qwen3-32B 8.3 M Llama-3.1-8B-Instruct 8.0 M

Appears in

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