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.

baidu logo

Can the Arc A310 run Unlimited-OCR-2?

Unlimited-OCR-2·3.3B (1.1B active)·Arc A310·4 GB VRAM

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

Yes. The Arc A310 runs Unlimited-OCR-2 fully in VRAM at Q4_K_M (about 2.8 GB of 4.0 GB).

best quant
Q4_K_M
needs
2.8 GB
usable
4.0 GB

Estimates from the model's size.Try other contexts on the Unlimited-OCR-2 page →

Every quantisation of Unlimited-OCR-2 on the Arc A310

QuantMemoryFit
Q4_K_M pick2.8 GBfits
Q8_0 4.0 GBtight
FP16 / BF16 7.1 GBtoo big

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

Run Unlimited-OCR-2 on the Arc A310

Using Q4_K_M, the best fit for Arc A310.

llama.cpp · OpenAI-compatible server with a web UIdocs
llama-server -hf RX5950XT/Unlimited-OCR-2-GGUF:Q4_K_M

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 RX5950XT/Unlimited-OCR-2-GGUF:Q4_K_M --host 0.0.0.0 --port 8080 -ngl 99

Server and web UI on port 8080.

Transformers · Ask about an imagedocs
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="baidu/Unlimited-OCR-2", 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
zai-org logoGLM-OCRzai-org
1.3BFP16 / BF16≈3.5 GBFits in memoryCommercial OK
1.3BFP16 / BF16≈3.4 GBFits in memoryCommercial OK
XingChen-AGI logoTeleOCRXingChen-AGI
1.4BFP16 / BF16≈3.7 GBFits in memoryCommercial OK
tencent logoHunyuanOCRtencent
1.1BFP16 / BF16≈3.0 GBFits in memoryConditions
PaddlePaddle logoPaddleOCR-VL-1.6PaddlePaddle
959MFP16 / BF16≈2.6 GBFits in memoryCommercial OK
1BFP16 / BF16≈2.8 GBFits in memoryCommercial OK

Other GPUs that run Unlimited-OCR-2

Frequently asked questions

Can the Arc A310 run Unlimited-OCR-2?
Yes. The Arc A310 runs Unlimited-OCR-2 fully in VRAM at Q4_K_M (about 2.8 GB of 4.0 GB).
Which quantisation of Unlimited-OCR-2 should I use on the Arc A310?
Q4_K_M: the largest one that fits. Expected quality: small loss 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.