Qwen3.5-4B-Base: Self-Hosting & Deployment Guide
Qwen3.5-4B-Base is an open-weight vision-language model that reads images alongside text.
What is Qwen3.5-4B-Base?
Qwen3.5-4B-Base is an open-weight vision-language model that reads images alongside text, published by Alibaba Qwen with open weights at Qwen/Qwen3.5-4B-Base. LLM API does not route this model today, so there is no endpoint or code sample for it here. What this page does give you is the self-hosting picture: published weight sizes, the VRAM each quantisation needs and the commands to serve it yourself. Every figure is read from the public repository and refreshed weekly. At import it had 509,401 downloads on Hugging Face in the previous 30 days, under the apache-2.0 licence.
How to run Qwen3.5-4B-Base yourself
Open weights (apache-2.0), 4.7B parameters. Below: how much memory the weights need at each quantization, which hardware fits them, and the commands to serve it.
Qwen3.5-4B-Base VRAM requirements
| Precision / quantization | Weights | Figure | Source |
|---|---|---|---|
| BF16 (full precision) | 9.3 GB | Estimate | 4.7B params × 2 bytes |
| GGUF Q4_K_M | 2.7 GB | File size | mradermacher/Qwen3.5-4B-Base-i1-GGUF |
| GGUF Q2_K | 1.9 GB | File size | mradermacher/Qwen3.5-4B-Base-i1-GGUF |
File size = actual download size on Hugging Face. Estimate = parameter count × bytes per weight. Weights only — the KV cache for long contexts needs extra memory; the fit tables below add 15% headroom as a rule of thumb.
GPU requirements: deploy Qwen3.5-4B-Base on your hardware
| Hardware | BF16 (full precision) | GGUF Q4_K_M | GGUF Q2_K |
|---|---|---|---|
| NVIDIA H200141 GB | 1× | 1× | 1× |
| NVIDIA H10080 GB | 1× | 1× | 1× |
| NVIDIA A100 80GB80 GB | 1× | 1× | 1× |
| NVIDIA L40S48 GB | 1× | 1× | 1× |
GPUs needed per variant.
| Hardware | GGUF Q4_K_M | GGUF Q2_K |
|---|---|---|
| RTX 509032 GB | 1× | 1× |
| RTX 409024 GB | 1× | 1× |
| RTX 309024 GB | 1× | 1× |
GGUF via llama.cpp; more cards or CPU offload for larger files.
| Hardware | GGUF Q4_K_M | GGUF Q2_K |
|---|---|---|
| Mac, 512 GBM3 Ultra | Fits | Fits |
| Mac, 192 GBM2 Ultra | Fits | Fits |
| Mac, 128 GBM4 Max / M3 Max | Fits | Fits |
| Mac, 64 GBM4 Pro / Max | Fits | Fits |
Assumes ~75% of unified memory is usable by the GPU.
| Hardware | BF16 (full precision) | GGUF Q4_K_M | GGUF Q2_K |
|---|---|---|---|
| AWS p5.48xlarge8× H100 · 640 GB | Fits | Fits | Fits |
| AWS p4de.24xlarge8× A100 80GB · 640 GB | Fits | Fits | Fits |
| AWS g6e.12xlarge4× L40S · 192 GB | Fits | Fits | Fits |
| Google Cloud a3-highgpu-8g8× H100 · 640 GB | Fits | Fits | Fits |
| Azure ND H100 v58× H100 · 640 GB | Fits | Fits | Fits |
Whole-instance GPU memory; public instance specs.
Serve it yourself
pip install -U vllm
vllm serve Qwen/Qwen3.5-4B-Basepip install 'sglang[all]'
python -m sglang.launch_server --model-path Qwen/Qwen3.5-4B-Basellama-server -hf mradermacher/Qwen3.5-4B-Base-i1-GGUF:Q4_K_M \
--ctx-size 32768 --n-gpu-layers 99Commands use the official repositories above; vLLM and SGLang expose an OpenAI-compatible endpoint.
Not on LLM.API yet
We do not route this model through our API at the moment. Browse the models you can call today — most workloads have a close match already live.
Not available on LLM API yet
We do not route this model through our API at the moment, so there is no endpoint or code snippet for it yet. Browse the models you can call today — most workloads have a close match already live.
Browse available modelsWhen to Use — When NOT to Use
Use it if...
- You want to run Qwen3.5-4B-Base on your own hardware and keep every prompt inside your network
- The weights are published openly, so you can pin one checkpoint and keep it reproducible
- You want to fine-tune or quantise the model rather than accept a hosted configuration
- You process documents, screenshots or charts where the image must stay in-house
Avoid if...
- LLM API does not route this model today, so there is no endpoint here to call
- You have no GPU capacity: the VRAM figures below are the floor, not a suggestion
- You want zero operations — serving, scaling and upgrades are yours to run
- You need audio or video input; this checkpoint documents text and images only
Get one key to every model
Swap your API key. Keep your code.