Will It Run AI

AlibabaAlibaba

Qwen3-Coder 30B A3B Instruct

Frontier
huggingfaceHuggingFaceollamaOllama
1.9MDownloads1.1KLikesJul 2025Veröffentlicht256K TokenKontextApache 2.0Lizenz100 HerausragendQualität

Qwen3-Coder 30B A3B Instruct (30.5B parameters) requires approximately 21.9 GB of VRAM with Q4_K_M quantization. As a Mixture of Experts model with 3.299999952316284B active parameters, it uses less memory than its total parameter count suggests. For the best balance of quality and speed, we recommend hardware with at least 26 GB of VRAM.

Loslegen

— kopieren & einfügen, um lokal auszuführen

Copy-paste commands to run Qwen3-Coder 30B A3B Instruct on your machine.

Run

ollama run qwen3-coder

Quick specs

Parameters30.5B (3.3B active)
Architecturemoe (MoE)
Context256K tokens
Modalitytext
Min RAM11.9 GB
Rec. RAM18.6 GB (Q4_K_M)
LicenseApache 2.0
FamilyQwen Coder
✓ Code✓ Reasoning

About this model

Qwen3-Coder is available in multiple sizes. Today, we're excited to introduce Qwen3-Coder-30B-A3B-Instruct. This streamlined model maintains impressive performance and efficiency, featuring the following key enhancements:

  • •Significant Performance: among open models on Agentic Coding, Agentic Browser-Use, and other foundational coding tasks
  • •Long-context Capabilities: with native support for 256K tokens, extendable up to 1M tokens using Yarn, optimized for repository-scale...
  • •Agentic Coding: supporting for most platform such as Qwen Code, CLINE, featuring a specially designed function call format

Verwandte Modelle

Deine Hardware

Erkennung...

Schnellauswahl

Bestes BudgetS
Mac mini M4 64GB~$1,099 — 13 tok/s
NVIDIA
Beste GesamtwahlS
RTX 5090 32GB~$1,999 — 182 tok/s

Beste Hardware

Top-Empfehlungen für Qwen3-Coder 30B A3B Instruct

NVIDIA
RTX 5090 32GBS
32 GB
NVIDIA
RTX PRO 4500 Blackwell 32GBS
32 GB
NVIDIA
NVIDIA V100 32GBS
32 GB
AMD Instinct MI100 32GBS
32 GB
AMD Instinct MI60 32GBS
32 GB

Dieses Modell ausführen

Qwen3-Coder 30B A3B Instruct on RTX 5090 32GBQwen3-Coder 30B A3B Instruct on RTX PRO 4500 Blackwell 32GBQwen3-Coder 30B A3B Instruct on NVIDIA V100 32GB

Quantisierungsoptionen

VRAM-Schätzungen nach Quantisierungsstufe

No hardware detected — fit column shows raw VRAM estimates

QuantBitsVRAMQualityFit
Q2_K
2
11.9 GB
Low—
Q3_K_S
3
14.9 GB
Low—
NVFP4
4
17.1 GB
Medium—
Q4_K_M
4
18.6 GB
Medium—
Q5_K_M
5
22.0 GB
High—
Q6_K
6
25.0 GB
High—
Q8_0
8
32.6 GB
Very High—
F16
16
62.5 GB
Maximum—

Quality benchmarks

Qwen3-Coder 30B A3B Instruct benchmark scores

Benchmark verified

Coding

SWE-bench Verified51.6%
HumanEval+—
Aider Polyglot—
LiveCodeBench—

Hardware-Kompatibilität

Eignungsschätzungen für alle Hardware

Rechner öffnen

Computing compatibility...

Speicheraufschlüsselung

Reference: RTX 2060 6GB

Weights18.6 GB
KV Cache1.5 GB
Runtime1.2 GB
Headroom0.6 GB

Häufig gestellte Fragen

FAQ — Qwen3-Coder 30B A3B Instruct

Siehe auch

QuantisierungsleitfadenBewertungsmethodikRechner öffnen