Alibaba
Qwen 3.5 2B
前沿
Jun 2025发布日期131K tokens上下文Apache 2.0许可证54 良好质量
Qwen 3.5 2B (2B parameters) requires approximately 4.7 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 6 GB of VRAM.
快速开始
— 复制粘贴即可本地运行Copy-paste commands to run Qwen 3.5 2B on your machine.
Run
ollama run qwen3.5:2bQuick specs
Parameters2B
Architecturedense
Context131K tokens
Modalitytext
Min RAM0.8 GB
Rec. RAM1.2 GB (Q4_K_M)
LicenseApache 2.0
FamilyQwen
✓ Chat
About this model
- •Runs on virtually any GPU with 2+ GB VRAM at Q4_K_M
- •Strong chat and general assistant capabilities for its size
相关模型
快速推荐
最佳硬件
Qwen 3.5 2B 的最佳选择
运行此模型
量化选项
各量化级别的 VRAM 估算
No hardware detected — fit column shows raw VRAM estimates
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 0.8 GB | Low | — |
Q3_K_S | 3 | 1.0 GB | Low | — |
NVFP4 | 4 | 1.1 GB | Medium | — |
Q4_K_M | 4 | 1.2 GB | Medium | — |
Q5_K_M | 5 | 1.4 GB | High | — |
Q6_K | 6 | 1.6 GB | High | — |
Q8_0 | 8 | 2.1 GB | Very High | — |
F16 | 16 | 4.1 GB | Maximum | — |
Quality benchmarks
Qwen 3.5 2B benchmark scores
Reasoning
MMLU-Pro55.3%
GPQA Diamond51.6%
MATH-500—
ARC Challenge—
General
Chatbot Arena—
IFEval61.2%
Source: official · 2026-03-02
硬件兼容性
全部硬件的适配估算
Computing compatibility...
内存详细分析
Reference: RTX 2060 6GB
Weights1.2 GB
KV Cache1.7 GB
Runtime1.2 GB
Headroom0.6 GB
常见问题
FAQ — Qwen 3.5 2B
另请参阅