selfhost.directory

The index of self-hostable projects — ranked, categorized and served with live updates.
Own your data and stop giving it to big tech.

ATH-MaaS logo

Can the Arc A310 run OvisOCR3?

OvisOCR3·853M·Arc A310·4 GB VRAM

Saved in this browser, used on every model page.
Yes

Yes. The Arc A310 runs OvisOCR3 fully in VRAM at FP16 / BF16 (about 2.2 GB of 4.0 GB).

best quant
FP16 / BF16
needs
2.2 GB
usable
4.0 GB

Estimates from the model's size.Try other contexts on the OvisOCR3 page →

Every quantisation of OvisOCR3 on the Arc A310

QuantMemoryFit
Q4_K_M 1.1 GBfits
Q8_0 1.4 GBfits
FP16 / BF16 pick2.2 GBfits

Speed is a bandwidth-based estimate for generating text (124 GB/s); prompt processing and long contexts are slower.

Run OvisOCR3 on the Arc A310

Using FP16 / BF16, the best fit for Arc A310.

Ollama · F16 straight from Hugging Facedocs
ollama run hf.co/mradermacher/OvisOCR3-GGUF:F16

Ollama’s ROCm/CUDA builds don’t cover this GPU. Recent Ollama releases use Vulkan when its Vulkan backend and driver are installed (older ones needed OLLAMA_VULKAN=1); llama.cpp or LM Studio with Vulkan are the safer bet.

llama.cpp · OpenAI-compatible server with a web UIdocs
llama-server -hf mradermacher/OvisOCR3-GGUF:F16

Needs a Vulkan build of llama.cpp. Downloads the GGUF on first run.

llama.cpp · Docker with Vulkandocs
docker run -d --name llama --device /dev/dri -p 8080:8080 \
  -v ~/.cache/llama.cpp:/root/.cache/llama.cpp \
  ghcr.io/ggml-org/llama.cpp:server-vulkan \
  -hf mradermacher/OvisOCR3-GGUF:F16 --host 0.0.0.0 --port 8080 -ngl 99

Server and web UI on port 8080.

LM Studio · Download with the lms CLIdocs
lms get mradermacher/OvisOCR3-GGUF@F16

Then load it from the LM Studio app or with `lms load`.

Transformers · Ask about an imagedocs
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 Arc A310 comfortably

All that fit →
ModelParamsBest quantMemoryLicence
PaddlePaddle logoPaddleOCR-VL-1.6PaddlePaddle
959MFP16 / BF16≈2.6 GBFits in memoryCommercial OK
853MFP16 / BF16≈2.4 GBFits in memoryCommercial OK
PaddlePaddle logoPaddleOCR-VLPaddlePaddle
959MFP16 / BF16≈2.6 GBFits in memoryCommercial OK
1BFP16 / BF16≈2.8 GBFits in memoryCommercial OK
PaddlePaddle logoPaddleOCR-VL-1.5PaddlePaddle
959MFP16 / BF16≈2.6 GBFits in memoryCommercial OK
tencent logoHunyuanOCRtencent
1.1BFP16 / BF16≈3.0 GBFits in memoryConditions

Other GPUs that run OvisOCR3

Frequently asked questions

Can the Arc A310 run OvisOCR3?
Yes. The Arc A310 runs OvisOCR3 fully in VRAM at FP16 / BF16 (about 2.2 GB of 4.0 GB).
Which quantisation of OvisOCR3 should I use on the Arc A310?
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.