Skip to content

Qwen 3.5 2B

by Alibaba · qwen-3.5 family

2B

parameters

text-generation code-generation reasoning multilingual vision

Qwen 3.5 2B is a compact multimodal model that punches above its weight class. It handles text and vision tasks with 256K context across 201 languages. Needs about 3 GB of VRAM at Q4, making it a strong choice for laptops and entry-level hardware where you want more capability than a sub-1B model.

Quick Start with Ollama

ollama run 2b-q4_K_M
Resources Ollama Hugging Face Official Page
Creator Alibaba
Parameters 2B
Architecture transformer-decoder
Context 256K tokens
Released Mar 2, 2026
License Apache 2.0
Ollama qwen3.5:2b

Quantization Options

Format File Size VRAM Required Quality Ollama Tag
Q4_K_M rec 2.7 GB 3 GB 2b-q4_K_M
Q8_0 4 GB 4.5 GB 2b-q8_0

Compatible Hardware

Q4_K_M requires 3 GB VRAM

Compatible Hardware

HardwareVRAMTypeFitEst. Speed
Mac Studio M4 Ultra 512GB512 GBmacRuns~273 tok/s
Mac Pro M2 Ultra 192GB192 GBmacRuns~267 tok/s
Mac Studio M4 Ultra 192GB192 GBmacRuns~273 tok/s
Mac Studio M4 Max 128GB128 GBmacRuns~182 tok/s
MacBook Pro M4 Max 128GB128 GBmacRuns~182 tok/s
MacBook Pro M5 Max 128GB128 GBmacRuns~182 tok/s
NVIDIA RTX PRO 6000 Blackwell96 GBgpuRuns~640 tok/s
MacBook Pro M3 Max 96GB96 GBmacRuns~133 tok/s
Mac mini M4 Pro 64GB64 GBmacRuns~91 tok/s
Mac Studio M4 Max 64GB64 GBmacRuns~182 tok/s
MacBook Pro M4 Max 64GB64 GBmacRuns~182 tok/s
MacBook Pro M5 Max 64GB64 GBmacRuns~182 tok/s
NVIDIA RTX 6000 Ada Generation48 GBgpuRuns~320 tok/s
NVIDIA RTX A600048 GBgpuRuns~256 tok/s
NVIDIA RTX PRO 5000 Blackwell48 GBgpuRuns~320 tok/s
Mac mini M4 Pro 48GB48 GBmacRuns~91 tok/s
MacBook Pro M3 Max 48GB48 GBmacRuns~133 tok/s
MacBook Pro M4 Max 48GB48 GBmacRuns~182 tok/s
MacBook Pro M4 Pro 48GB48 GBmacRuns~91 tok/s
MacBook Pro M5 Max 48GB48 GBmacRuns~137 tok/s
MacBook Pro M5 Pro 48GB48 GBmacRuns~91 tok/s
Mac Studio M4 Max 36GB36 GBmacRuns~182 tok/s
MacBook Pro M3 Pro 36GB36 GBmacRuns~50 tok/s
MacBook Pro M5 Max 36GB36 GBmacRuns~137 tok/s
NVIDIA RTX 5000 Ada Generation32 GBgpuRuns~241 tok/s
NVIDIA GeForce RTX 509032 GBgpuRuns~597 tok/s
iMac M4 32GB32 GBmacRuns~40 tok/s
Mac mini M4 32GB32 GBmacRuns~40 tok/s
MacBook Air M4 32GB32 GBmacRuns~40 tok/s
MacBook Air M5 32GB32 GBmacRuns~40 tok/s
MacBook Pro M5 32GB32 GBmacRuns~40 tok/s
AMD Radeon RX 7900 XTX24 GBgpuRuns~320 tok/s
NVIDIA GeForce RTX 309024 GBgpuRuns~312 tok/s
NVIDIA GeForce RTX 3090 Ti24 GBgpuRuns~336 tok/s
NVIDIA GeForce RTX 409024 GBgpuRuns~336 tok/s
NVIDIA RTX A500024 GBgpuRuns~256 tok/s
iMac M3 24GB24 GBmacRuns~33 tok/s
Mac mini M2 24GB24 GBmacRuns~33 tok/s
Mac mini M4 Pro 24GB24 GBmacRuns~91 tok/s
MacBook Air M2 24GB24 GBmacRuns~33 tok/s
MacBook Air M4 24GB24 GBmacRuns~40 tok/s
MacBook Air M5 24GB24 GBmacRuns~40 tok/s
MacBook Pro M4 Pro 24GB24 GBmacRuns~91 tok/s
MacBook Pro M5 24GB24 GBmacRuns~40 tok/s
MacBook Pro M5 Pro 24GB24 GBmacRuns~91 tok/s
AMD Radeon RX 7900 XT20 GBgpuRuns~267 tok/s
NVIDIA RTX 4000 Ada Generation20 GBgpuRuns~120 tok/s
MacBook Pro M3 Pro 18GB18 GBmacRuns~50 tok/s
AMD Radeon RX 6900 XT16 GBgpuRuns~171 tok/s
AMD Radeon RX 6800 XT16 GBgpuRuns~171 tok/s
AMD Radeon RX 7800 XT16 GBgpuRuns~208 tok/s
AMD Radeon RX 9060 XT 16GB16 GBgpuRuns~179 tok/s
AMD Radeon RX 9070 XT16 GBgpuRuns~217 tok/s
AMD Radeon RX 907016 GBgpuRuns~179 tok/s
Intel Arc A77016 GBgpuRuns~187 tok/s
NVIDIA GeForce RTX 4060 Ti 16GB16 GBgpuRuns~96 tok/s
NVIDIA GeForce RTX 4070 Ti Super16 GBgpuRuns~224 tok/s
NVIDIA GeForce RTX 4080 Super16 GBgpuRuns~245 tok/s
NVIDIA GeForce RTX 408016 GBgpuRuns~239 tok/s
NVIDIA GeForce RTX 5060 Ti 16GB16 GBgpuRuns~149 tok/s
NVIDIA GeForce RTX 5070 Ti16 GBgpuRuns~299 tok/s
NVIDIA GeForce RTX 508016 GBgpuRuns~320 tok/s
NVIDIA RTX A400016 GBgpuRuns~149 tok/s
iMac M1 16GB16 GBmacRuns~23 tok/s
iMac M4 16GB16 GBmacRuns~40 tok/s
Mac mini M1 16GB16 GBmacRuns~23 tok/s
Mac mini M4 16GB16 GBmacRuns~40 tok/s
MacBook Air M2 16GB16 GBmacRuns~33 tok/s
MacBook Air M3 16GB16 GBmacRuns~33 tok/s
MacBook Air M4 16GB16 GBmacRuns~40 tok/s
MacBook Air M5 16GB16 GBmacRuns~40 tok/s
MacBook Pro M1 16GB16 GBmacRuns~23 tok/s
MacBook Pro M2 Pro 16GB16 GBmacRuns~67 tok/s
MacBook Pro M5 16GB16 GBmacRuns~40 tok/s
AMD Radeon RX 6700 XT12 GBgpuRuns~128 tok/s
AMD Radeon RX 7700 XT12 GBgpuRuns~144 tok/s
Intel Arc B58012 GBgpuRuns~152 tok/s
NVIDIA GeForce RTX 3060 12GB12 GBgpuRuns~120 tok/s
NVIDIA GeForce RTX 3080 12GB12 GBgpuRuns~304 tok/s
NVIDIA GeForce RTX 4070 Super12 GBgpuRuns~168 tok/s
NVIDIA GeForce RTX 4070 Ti12 GBgpuRuns~168 tok/s
NVIDIA GeForce RTX 407012 GBgpuRuns~168 tok/s
NVIDIA GeForce RTX 507012 GBgpuRuns~224 tok/s
NVIDIA GeForce GTX 1080 Ti11 GBgpuRuns~161 tok/s
NVIDIA GeForce RTX 2080 Ti11 GBgpuRuns~205 tok/s
Intel Arc B57010 GBgpuRuns~127 tok/s
NVIDIA GeForce RTX 3080 10GB10 GBgpuRuns~253 tok/s
AMD Radeon RX 6600 XT8 GBgpuRuns~85 tok/s
AMD Radeon RX 76008 GBgpuRuns~96 tok/s
AMD Radeon RX 9060 XT 8GB8 GBgpuRuns~90 tok/s
Intel Arc A7508 GBgpuRuns~171 tok/s
NVIDIA GeForce GTX 10708 GBgpuRuns~85 tok/s
NVIDIA GeForce RTX 2060 Super8 GBgpuRuns~149 tok/s
NVIDIA GeForce RTX 2070 Super8 GBgpuRuns~149 tok/s
NVIDIA GeForce RTX 2080 Super8 GBgpuRuns~165 tok/s
NVIDIA GeForce RTX 30508 GBgpuRuns~75 tok/s
NVIDIA GeForce RTX 30708 GBgpuRuns~149 tok/s
NVIDIA GeForce RTX 3060 Ti8 GBgpuRuns~149 tok/s
NVIDIA GeForce RTX 4060 Ti 8GB8 GBgpuRuns~96 tok/s
NVIDIA GeForce RTX 40608 GBgpuRuns~91 tok/s
NVIDIA GeForce RTX 50508 GBgpuRuns~75 tok/s
NVIDIA GeForce RTX 5060 Ti 8GB8 GBgpuRuns~149 tok/s
NVIDIA GeForce RTX 50608 GBgpuRuns~112 tok/s
MacBook Air M1 8GB8 GBmacRuns~23 tok/s
MacBook Air M2 8GB8 GBmacRuns~33 tok/s
NVIDIA GeForce GTX 1660 Super6 GBgpuRuns~112 tok/s
NVIDIA GeForce RTX 20606 GBgpuRuns~112 tok/s