Qwen3-Coder-480B-A35B-Instruct
- In Input modalities: Text Out Output modalities: Text
- Tool use
- Structured output
- Open weights
Prices
3 offerings · prices as listedqwen3-coder-480b-a35b-instruct| Conditions/ 1M tokens | Input | Output |
|---|---|---|
| Standard no longer listed since Oct 11, 2026 | $1.50 | $7.50 |
| Prompts over 32K tokens no longer listed since Oct 11, 2026 | $2.70 | $13.50 |
| Prompts over 128K tokens no longer listed since Oct 11, 2026 | $4.50 | $22.50 |
Prices from qwen3-coder-480b-a35b-instruct model (opens in a new tab) (checked Oct 8, 2026)
qwen3-coder-480b-a35b-instruct| Conditions/ 1M tokens | Input | Output |
|---|---|---|
| Standard no longer listed since Oct 11, 2026 | $0.861 | $3.441 |
| Prompts over 32K tokens no longer listed since Oct 11, 2026 | $1.291 | $5.161 |
| Prompts over 128K tokens no longer listed since Oct 11, 2026 | $2.151 | $8.602 |
Prices from Alibaba Cloud Model Studio pricing (opens in a new tab) (checked Oct 11, 2026)
qwen3-coder-480b-a35b-instruct| Conditions/ 1M tokens | Input | Output |
|---|---|---|
| Standard no longer listed since Oct 11, 2026 | ¥6.00 | ¥24.00 |
| Prompts over 32K tokens no longer listed since Oct 11, 2026 | ¥9.00 | ¥36.00 |
| Prompts over 128K tokens no longer listed since Oct 11, 2026 | ¥15.00 | ¥60.00 |
Prices from 阿里云百炼：模型价格 (opens in a new tab) (checked Oct 6, 2026)
Standard: the price a request with no conditions pays (the headline price elsewhere on the site).
Details
- Max input
- 204.8K
- Reasoning
- —
- Knowledge cutoff
- Apr 2025
- Family
- qwen-coder
- Model ID
Not stated on Alibaba Qwen’s pages: reasoning efforts, reasoning can be off, max thinking budget, built-in tools, licence, aliases.
Run locally
Weights: Qwen/Qwen3-Coder-480B-A35B-Instruct- Parameters 480.2B
- Active 35B · 160 experts, 8 per token
- Native precision BF16
- Layers 62
- KV cache per token 248 KB
- Native context 256K (model card)
- Config positions 256K (config.json max_position_embeddings)
- API context 256K (maker’s API)
- Needs
- ≈ 251.4 GB (weights 237.6 + KV cache 1.9 + overhead 11.9)
- Usable
- 21.6 GB (90% of its memory)
- Try
- it’s too large for this hardware; see the smallest that runs it below
| Precision | Weights | Needs at 8K | On your hardware | Longest context |
|---|---|---|---|---|
| BF16 (native) | 894.4 GB | ≈ 941.0 | ✕Doesn’t fit | — |
| Q8_0 | 475.1 GB | ≈ 500.8 | ✕Doesn’t fit | — |
| FP8maker’s file | 449.0 GB | ≈ 473.4 | ✕Doesn’t fit | — |
| Q6_K | 367.2 GB | ≈ 387.5 | ✕Doesn’t fit | — |
| Q5_K_M | 318.1 GB | ≈ 335.9 | ✕Doesn’t fit | — |
| Q5_0 | 307.4 GB | ≈ 324.7 | ✕Doesn’t fit | — |
| Q4_K_M | 271.7 GB | ≈ 287.2 | ✕Doesn’t fit | — |
| Q4_0 | 251.5 GB | ≈ 266.1 | ✕Doesn’t fit | — |
| IQ4_XS | 237.6 GB | ≈ 251.4 | ✕Doesn’t fit | — |
| Q3_K_Mquality drops | 218.6 GB | ≈ 231.4 | ✕Doesn’t fit | — |
| IQ3_XXSquality drops | 171.0 GB | ≈ 181.5 | ✕Doesn’t fit | — |
| Q2_Kquality drops | 167.7 GB | ≈ 178.0 | ✕Doesn’t fit | — |
| IQ2_XXSquality drops | 115.1 GB | ≈ 122.8 | ✕Doesn’t fit | — |
Click a row to choose a precision. “Maker’s file” sizes are the maker’s own files; others are parameters × bits per weight.
Compared with other hardware
Each at the highest precision it runs. Click one for details.
Smallest that runs it (Q4_K_M, 8K): no single listed GPU; unified memory Apple M5 Ultra (80-core GPU) · 512 GB.
Run commands
The maker publishes no files at this precision. Choose its native precision or one of its own builds, or quantise it yourself with llama.cpp.
Memory to fine-tune
Batch 1, 2,048-token sequences, gradient checkpointing; LoRA and QLoRA train rank-16 adapters on the attention projections.
Estimates; facts from the maker’s Hugging Face repositories, as of 2026-11-06. How it’s estimated
Cited scores
From third-party leaderboards, not measured by us- LMArena Text 1,388
#111 of 163 listed models · CI 1,383–1,393 · 25,190 votes
- LMArena Text · Chinese 1,405
#111 of 161 listed models · CI 1,391–1,420 · 1,790 votes
- LMArena Text · Coding 1,457
#91 of 163 listed models · CI 1,448–1,466 · 4,805 votes
- LMArena Text · Creative writing 1,362
#100 of 163 listed models · CI 1,351–1,373 · 3,241 votes
- LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Oct 28, 2026
- changes we made
Changes
All changes →- Context window 256K → 262.14K
Sources
- Alibaba Cloud Model Studio pricing (opens in a new tab) alibabacloud.com · checked Oct 11, 2026
- 阿里云百炼：模型价格in Chinese (opens in a new tab) help.aliyun.com · checked Oct 6, 2026
- Text generation models - Qwen, DeepSeek, GLM | Model Studio - Alibaba Cloud Model Studio - Alibaba Cloud Documentation Center (opens in a new tab) alibabacloud.com · checked Oct 10, 2026
- 模型上下架与更新-大模型服务平台百炼-阿里云_大模型服务平台百炼(Model Studio)-大模型服务平台百炼(Model Studio)-阿里云帮助中心in Chinese (opens in a new tab) help.aliyun.com · checked Oct 30, 2026
- models.dev: qwen3-coder-480b-a35b-instruct (community data, MIT) (opens in a new tab) github.com · checked Sep 30, 2026
- qwen3-coder-480b-a35b-instruct (opens in a new tab) docs.modelstudio.console.alibabacloud.com · checked Oct 7, 2026
- qwen3-coder-480b-a35b-instruct model (opens in a new tab) alibabacloud.com · checked Oct 8, 2026
- Qwen/Qwen3-Coder-480B-A35B-Instruct model card (opens in a new tab) huggingface.co · checked Oct 31, 2026
- Qwen/Qwen3-Coder-480B-A35B-Instruct config.json (opens in a new tab) huggingface.co · checked Oct 31, 2026
- Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8 files (opens in a new tab) huggingface.co · checked Oct 31, 2026
- Qwen/Qwen3-Coder-480B-A35B-Instruct README.md (opens in a new tab) huggingface.co · checked Nov 4, 2026
Alibaba Qwen’s official policies: data use, privacy, terms →
Some values on this page are still waiting to be checked against official pages: a filled dot is verified, a hollow one is not yet (with or without a source on file). How we verify data
Alibaba Qwen · China · qwen.ai
Related models
Snapshots, the same family and other models from this provider