Qwen3 Next 80B A3B Instruct

Tool callingStructured output

Hugging Face Launch post Website Docs

Qwen instruction model for multilingual chat, reasoning, and tool use

Context: 262K
Released: 1y ago
Parameters: 80B
Input / 1M tokens: $0.10
Output / 1M tokens: $1.10
Cached input / 1M tokens: $0.07

Sources:models.devOpenRouter

Benchmarks

DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.

Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.

No benchmark results have been matched to this model yet.

Specifications

Developer: Qwen
Model family: Qwen
Type: Language model
Predecessor: —
Successor: —
Released: September 1, 2025
Model ID: qwen/qwen3-next-80b-a3b-instruct
Openness: Open weights
License: —
Parameters: 80B
Input modalities: text
Output modalities: text
Modality: text->text
Native context: 256K
Tokenizer: Qwen3
Max output tokens: 236K
Knowledge cutoff: 2025-04
Hugging Face: Qwen/Qwen3-Next-80B-A3B-Instruct
Source freshness: Metadata synced Oct 8, 2026, 10:17 PM UTC

Open-weight builds

Ollama variants

Every published Ollama tag matched to this model, including parameter editions, instruction/base variants, and quantized builds.

6 builds

Variant	Parameters	Type	Quantization	Size	Context	Input
qwen3-next:80b-a3b-instruct-fp16	80B	instruct	FP16	159 GB	256K	text
qwen3-next:80b-a3b-instruct-q4_K_M	80B	instruct	Q4_K_M	50 GB	256K	text
qwen3-next:80b-a3b-instruct-q8_0	80B	instruct	Q8_0	85 GB	256K	text
qwen3-next:80b-a3b-thinking-fp16	80B	thinking	FP16	159 GB	256K	text
qwen3-next:latest	80B	thinking	Q4_K_M	50 GB	256K	text
qwen3-next:80b-a3b-thinking-q8_0	80B	thinking	Q8_0	85 GB	256K	text

Additional source evidence

Source model: alibaba/qwen3-next-80b-a3b-instruct
Source family: qwen
Last updated: 2025-09
Knowledge cutoff: 2025-04
Model context: 131K
Model output limit: 33K
Open weights: Yes
File attachments: No
Reasoning: No
Tool calling: Yes
Temperature control: Yes

Downloadable weights

Hugging Face

Complete source record (JSON)

{
  "id": "alibaba/qwen3-next-80b-a3b-instruct",
  "name": "Qwen3-Next 80B-A3B Instruct",
  "description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
  "family": "qwen",
  "last_updated": "2025-09",
  "knowledge": "2025-04",
  "attachment": false,
  "reasoning": false,
  "tool_call": true,
  "temperature": true,
  "modalities": {
    "input": [
      "text"
    ],
    "output": [
      "text"
    ]
  },
  "limit": {
    "context": 131072,
    "output": 32768
  },
  "release_date": "2025-09",
  "open_weights": true,
  "weights": [
    {
      "label": "Hugging Face",
      "url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct"
    }
  ]
}

Infrastructure

Provider availability

All providers

Provider	Endpoint	Context	Input /M tokens	Output /M tokens	Cached input /M tokens	Cache write /M tokens	Uptime 1d	Data handling
DeepInfra	deepinfra/fp8	262K	$0.09	$1.10	—	—	96.94%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Parasail	parasail/fp8	262K	$0.10	$1.10	$0.07	—	99.93%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Google	google-vertex/global	262K	$0.15	$1.20	—	—	97.30%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15

Provider data:OpenRouter

Deployment graph

Can I run this?

Vertical Tabs only shows compatibility when it has structured evidence tying this exact model to hardware, runtime, quantization, memory use, and observed performance.

Browse hardware