AlibabaAlibaba

Qwen 3.5 0.6B

Frontier
Jun 2025Veröffentlicht131K TokenKontextApache 2.0Lizenz13 EinstiegQualität

Qwen 3.5 0.6B (0.6000000238418579B parameters) requires approximately 3.0 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 4 GB of VRAM.

Loslegen

— kopieren & einfügen, um lokal auszuführen

Copy-paste commands to run Qwen 3.5 0.6B on your machine.

Run

ollama run qwen3.5:0.6b

Quick specs

Parameters0.6B
Architecturedense
Context131K tokens
Modalitytext
Min RAM0.2 GB
Rec. RAM0.4 GB (Q4_K_M)
LicenseApache 2.0
FamilyQwen
Chat

About this model

Qwen3.5 is the latest generation of Alibaba's Qwen large language model family, bringing major improvements in reasoning, instruction following, and multilingual capability across both dense and MoE architectures.

  • Ultra-lightweight model ideal for edge devices and mobile deployment
  • Improved reasoning and instruction following over Qwen3 at same size

Verwandte Modelle

Deine Hardware

Erkennung...

Schnellauswahl

Beste Hardware

Top-Empfehlungen für Qwen 3.5 0.6B

Dieses Modell ausführen

Quantisierungsoptionen

VRAM-Schätzungen nach Quantisierungsstufe

No hardware detected — fit column shows raw VRAM estimates

QuantBitsVRAMQualityFit
Q2_K
2
0.2 GB
Low
Q3_K_S
3
0.3 GB
Low
NVFP4
4
0.3 GB
Medium
Q4_K_M
4
0.4 GB
Medium
Q5_K_M
5
0.4 GB
High
Q6_K
6
0.5 GB
High
Q8_0
8
0.6 GB
Very High
F16
16
1.2 GB
Maximum

Quality benchmarks

Qwen 3.5 0.6B benchmark scores

Benchmark verified

Reasoning

MMLU-Pro29.7%
GPQA Diamond
MATH-500
ARC Challenge

General

Chatbot Arena
IFEval52.1%

Source: official · 2026-03-02

Hardware-Kompatibilität

Eignungsschätzungen für alle Hardware

Rechner öffnen

Computing compatibility...

Speicheraufschlüsselung

Reference: RTX 2060 6GB

Weights0.4 GB
KV Cache0.9 GB
Runtime1.2 GB
Headroom0.6 GB

Häufig gestellte Fragen

FAQ — Qwen 3.5 0.6B

Siehe auch