Qwen3 vs Qwen3.5
Qwen3 and Qwen3.5 side by side: model sizes, the VRAM you need, context window, abilities, licence and which one to pick.
Side by side
| Qwen3 | Qwen3.5 | |
|---|---|---|
| Type | Model in the Qwen family | Model in the Qwen family |
| Developer | Alibaba Cloud (Qwen team) | Alibaba Cloud (Qwen team) |
| Released | Apr 2025 | Feb 2026 |
| Parameters | 0.6B–235B | 0.8B–122B |
| Sizes | 0.6B · 1.7B · 4B · 8B · 14B · 30B · 32B · 235B | 0.8B · 2B · 4B · 9B · 27B · 35B · 122B |
| Smallest VRAM (4-bit) | ~1.5 GB | ~2 GB |
| Context window | 256K tokens | 256K tokens |
| Abilities | Tool callingReasoning mode | Tool callingReasoning modeImage input |
| Licence | Apache 2.0 | Apache 2.0 |
| Run it | ollama run qwen3:0.6b | ollama run qwen3.5:0.8b |
Which one should you pick?
- Qwen3 runs on smaller hardware: from ~1.5 GB of GPU memory, against ~2 GB.
- Only Qwen3.5 has image input.
Pick Qwen3 if…
- you have less GPU memory (it starts at 1.5 GB)
- your tools or fine-tunes already target it (released Apr 2025, so support is mature)
Best for: Text models with a thinking mode; huge install base
Pick Qwen3.5 if…
- you need image input
- you want the newer model (Feb 2026)
Best for: Multimodal family from 0.8B to 122B, best for small GPUs
VRAM and download size
Ollama's default 4-bit builds with an 8K context. Read GB as system RAM on a CPU-only machine or a Mac.
Qwen3
| Model | Download | VRAM |
|---|---|---|
| 0.6B | 523 MB | ~1.5 GB |
| 1.7B | 1.4 GB | ~2.5 GB |
| 4B | 2.5 GB | ~3.5 GB |
| 8B | 5.2 GB | ~6.5 GB |
| 14B | 9.3 GB | ~11 GB |
| 30B | 19 GB | ~21.5 GB |
| 32B | 20 GB | ~22.5 GB |
| 235B | 142 GB | ~157 GB |
Qwen3.5
| Model | Download | VRAM |
|---|---|---|
| 0.8B | 1.3 GB | ~2 GB |
| 2B | 2.6 GB | ~3.5 GB |
| 4B | 4.1 GB | ~5.5 GB |
| 9B | 9 GB | ~10.5 GB |
| 27B | 21 GB | ~24 GB |
| 35B | 24 GB | ~27 GB |
| 122B | 81 GB | ~90 GB |
Frequently asked questions
Is Qwen3 better than Qwen3.5?
It depends on the job and your hardware. Qwen3 runs on smaller hardware: from ~1.5 GB of GPU memory, against ~2 GB. Only Qwen3.5 has image input. For quality, test both on your own prompts: benchmark rankings change with every release.
Which needs less VRAM, Qwen3 or Qwen3.5?
Qwen3 starts at ~1.5 GB (523 MB download). Qwen3.5 starts at ~2 GB (1.3 GB download).
Can I use Qwen3 and Qwen3.5 commercially?
Qwen3: Apache 2.0. Qwen3.5: Apache 2.0. Check the exact licence of the model you deploy; custom licences can limit very large companies or certain uses.
More comparisons
- Qwen vs Llama
- DeepSeek vs Qwen
- Gemma vs Llama
- gpt-oss vs Qwen
- Kimi vs DeepSeek
- GLM vs Qwen
- Mistral vs Llama
- Qwen Coder vs Devstral
- Claude vs GPT
- Claude vs Gemini
- Gemini vs GPT
- Phi vs Gemma
- Nemotron vs Qwen
- Llama 3.1 vs Llama 4
- Gemma 3 vs Gemma 4
- Qwen3.6 vs Qwen3.8
- Gemma 4 vs Qwen3.5
- DeepSeek-R1 vs Qwen3
- gpt-oss vs Qwen3.8
- Muse Glimmer vs Qwen3.8
- Qwen3-Coder vs Devstral Small 2