Yes. The Tesla T4 runs OvisOCR3 fully in VRAM at FP16 / BF16 (about 2.2 GB of 16 GB).
- best quant
- FP16 / BF16
- needs
- 2.2 GB
- usable
- 16 GB
Estimates from the model's size.Try other contexts on the OvisOCR3 page →
Every quantisation of OvisOCR3 on the Tesla T4
| Quant | Memory | Fit |
|---|---|---|
| Q4_K_M | 1.1 GB | fits |
| Q8_0 | 1.4 GB | fits |
| FP16 / BF16 pick | 2.2 GB | fits |
Speed is a bandwidth-based estimate for generating text (320 GB/s); prompt processing and long contexts are slower.
Run OvisOCR3 on the Tesla T4
Using FP16 / BF16, the best fit for Tesla T4.
ollama run hf.co/mradermacher/OvisOCR3-GGUF:F16 llama-server -hf mradermacher/OvisOCR3-GGUF:F16Downloads the GGUF on first run. Installed through llama.app? The same flags work with `llama serve`.
lms get mradermacher/OvisOCR3-GGUF@F16Then load it from the LM Studio app or with `lms load`.
vllm serve ATH-MaaS/OvisOCR3 vllm serve leleroyn/OvisOCR3-AWQ-W4A16services:
vllm:
image: vllm/vllm-openai:latest
command: ATH-MaaS/OvisOCR3
ports:
- "8000:8000"
ipc: host
volumes:
- ~/.cache/huggingface:/root/.cache/huggingface
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: all
capabilities: [gpu]API on port 8000.
sglang serve ATH-MaaS/OvisOCR3 --host 0.0.0.0 --port 30000services:
sglang:
image: lmsysorg/sglang:latest
command: sglang serve ATH-MaaS/OvisOCR3 --host 0.0.0.0 --port 30000
ports:
- "30000:30000"
ipc: host
volumes:
- ~/.cache/huggingface:/root/.cache/huggingface
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: all
capabilities: [gpu]API on port 30000.
from transformers import pipeline
pipe = pipeline("image-text-to-text", model="ATH-MaaS/OvisOCR3", dtype="auto", device_map="auto")
messages = [
{
"role": "user",
"content": [
{"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"},
{"type": "text", "text": "Describe this image."},
],
}
]
out = pipe(text=messages, max_new_tokens=256)
print(out[0]["generated_text"][-1]["content"])OCR models that fit the Tesla T4 comfortably
All that fit →| Model | Params | Best quant | Memory |
|---|---|---|---|
| 959M | FP16 / BF16 | ≈2.6 GBFits in memory | |
| 959M | FP16 / BF16 | ≈2.6 GBFits in memory | |
| 1.1B | FP16 / BF16 | ≈3.0 GBFits in memory | |
| 1B | FP16 / BF16 | ≈2.8 GBFits in memory | |
| 853M | FP16 / BF16 | ≈2.4 GBFits in memory | |
| 689M | FP16 / BF16 | ≈2.0 GBFits in memory |
Other GPUs that run OvisOCR3
Frequently asked questions
- Can the Tesla T4 run OvisOCR3?
- Yes. The Tesla T4 runs OvisOCR3 fully in VRAM at FP16 / BF16 (about 2.2 GB of 16 GB).
- Which quantisation of OvisOCR3 should I use on the Tesla T4?
- FP16 / BF16: the largest one that fits. Expected quality: lossless compared with the full-precision weights.
Memory and speed are estimates from the model's size and the card's memory bandwidth; real numbers depend on the runtime, drivers and context length. Community figures are medians of user reports.