Qwen / text-generation Open weights Also via API updated 9 months ago

Qwen3-Coder-Next

Name: Qwen3-Coder-Next
Price: 0.12 USD
Author: Qwen

Today, we're announcing Qwen3-Coder-Next, an open-weight language model designed specifically for coding agents and local development. It features the following key enhancements:

Params

79.7 B

Context

262,144

Downloads 30d

426 K

Likes

1,739

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

Download history

daily snapshots · 106 days

▲ 168 K in the last 30 days (28.3%)

729 K385 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	159.4 GB	187.7 GB	❌ Won’t fit
model.safetensors (bf16, full)	bf16 + 256K ctx	159.4 GB	558.2 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/qwen3-coder-next
{
  "hf_id": "Qwen/Qwen3-Coder-Next",
  "params_b": 79.67,
  "context_length": 262144,
  "license": { "id": "apache-2.0", "commercial": "yes" },
  "downloads_30d": 426195,
  "vram_estimates": [
    { "quant": "bf16", "gb": 187.7 }
  ],
  "updated_at": "2026-07-28T18:04:12Z"
}

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

Use via API

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

$0.12

input / 1M

$0.80

output / 1M

$0.07

cached input / 1M

$0.92

1M in + 1M out

Context window: 262,144 tokens
Max output: 235,929 tokens
Providers: 1
Cheapest provider: Parasail · $0.12 / $0.80
Best throughput: —
AA Intelligence / Coding / Agentic: — / 36.2 / 0.9

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

Specifications

Architecture: Qwen3NextForCausalLM
Parameters: 79.7 B
Tensor type: BF16
Context length: 262,144
Vocabulary: 151,936
Layers / heads: 48 / 16
Licence: apache-2.0
First seen on the Hub: 2026-01-30
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Family

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

Derivative Qwen3-Coder-Next-8bit NexVeridian 336 K Derivative Qwen3-Coder-Next-FP8 unsloth 192 K Derivative Qwen3-Coder-Next-GGUF unsloth 177 K Derivative Qwen3-Coder-Next-FP8-dynamic RedHatAI 170 K

Compare with any text-generation model

Popular comparisons

gpt-oss-20b 5.8 M dolphin-2.9.1-yi-1.5-34b 4.8 M Qwen3-32B 3.0 M gpt-oss-120b 2.4 M Qwen3-32B-AWQ 222 K DeepSeek-V4-Flash-NVFP4 203 K

Appears in

Best open coding models