Will It Run AI

AlibabaAlibaba

Qwen 3 235B A22B

Frontier
huggingfaceHuggingFace
135.0KDownloads782LikesApr 2025Veröffentlicht131K TokenKontextApache 2.0Lizenz89 StarkQualität

Qwen 3 235B A22B (235B parameters) requires approximately 147.7 GB of VRAM with Q4_K_M quantization. As a Mixture of Experts model with 22B 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 170 GB of VRAM.

Loslegen

— kopieren & einfügen, um lokal auszuführen

Copy-paste commands to run Qwen 3 235B A22B on your machine.

Run

lms load Qwen3-235B-A22B-Instruct-2507 && lms server start

Quick specs

Parameters235B (22B active)
Architecturemoe (MoE)
Context131K tokens
Modalitytext
Min RAM91.7 GB
Rec. RAM143.4 GB (Q4_K_M)
LicenseApache 2.0
FamilyQwen
✓ Chat✓ Reasoning

About this model

We introduce the updated version of the Qwen3-235B-A22B non-thinking mode, named Qwen3-235B-A22B-Instruct-2507, featuring the following key enhancements:

  • •Significant improvements: in general capabilities, including **instruction following, logical reasoning, text comprehension, mathematics, science,...
  • •Substantial gains: in long-tail knowledge coverage across multiple languages
  • •Markedly better alignment: with user preferences in subjective and open-ended tasks, enabling more helpful responses and higher-quality text...
  • •Enhanced capabilities: in 256K long-context understanding

Verwandte Modelle

Deine Hardware

Erkennung...

Schnellauswahl

Bestes BudgetS
Mac Studio M3 Ultra 256GB~$6,999 — 11 tok/s
Beste GesamtwahlS
AMD Instinct MI325X 256GB~$20,000 — 89 tok/s

Beste Hardware

Top-Empfehlungen für Qwen 3 235B A22B

AMD Instinct MI325X 256GBS
256 GB
AMD Instinct MI350X 288GBS
288 GB
NVIDIA
NVIDIA B200 180GBS
180 GB
NVIDIA
NVIDIA GB200 192GBS
192 GB
NVIDIA
B100 192GBS
192 GB

Dieses Modell ausführen

Qwen 3 235B A22B on AMD Instinct MI325X 256GBQwen 3 235B A22B on AMD Instinct MI350X 288GBQwen 3 235B A22B on NVIDIA B200 180GB

Quantisierungsoptionen

VRAM-Schätzungen nach Quantisierungsstufe

No hardware detected — fit column shows raw VRAM estimates

QuantBitsVRAMQualityFit
Q2_K
2
91.7 GB
Low—
Q3_K_S
3
115.2 GB
Low—
NVFP4
4
131.6 GB
Medium—
Q4_K_M
4
143.4 GB
Medium—
Q5_K_M
5
169.2 GB
High—
Q6_K
6
192.7 GB
High—
Q8_0
8
251.5 GB
Very High—
F16
16
481.7 GB
Maximum—

Quality benchmarks

Qwen 3 235B A22B benchmark scores

Benchmark verified

Coding

SWE-bench Verified—
HumanEval+—
Aider Polyglot57.3%
LiveCodeBench70.7%

Reasoning

MMLU-Pro83.0%
GPQA Diamond77.5%
MATH-50090.2%
ARC Challenge—

General

Chatbot Arena—
IFEval88.7%

Source: official · 2025-07-14

Hardware-Kompatibilität

Eignungsschätzungen für alle Hardware

Rechner öffnen

Computing compatibility...

Speicheraufschlüsselung

Reference: RTX 2060 6GB

Weights143.4 GB
KV Cache2.9 GB
Runtime0.9 GB
Headroom0.6 GB

Häufig gestellte Fragen

FAQ — Qwen 3 235B A22B

Siehe auch

QuantisierungsleitfadenBewertungsmethodikRechner öffnen