Can the Arc B580 run surya-ocr-2.5?
surya-ocr-2.5·689M·Arc B580·12 GB VRAM
Yes. The Arc B580 runs surya-ocr-2.5 fully in VRAM at FP16 / BF16 (about 2.0 GB of 12 GB).
- best quant
- FP16 / BF16
- needs
- 2.0 GB
- usable
- 12 GB
Estimates from the model's size.Try other contexts on the surya-ocr-2.5 page →
Every quantisation of surya-ocr-2.5 on the Arc B580
| Quant | Memory | Fit |
|---|---|---|
| Q4_K_M | 1.0 GB | fits |
| Q8_0 | 1.2 GB | fits |
| FP16 / BF16 pick | 2.0 GB | fits |
Speed is a bandwidth-based estimate for generating text (456 GB/s); prompt processing and long contexts are slower.
Run surya-ocr-2.5 on the Arc B580
Using Q8_0, the best fit for Arc B580.
ollama run hf.co/datalab-to/surya-ocr-2.5-gguf:Q8_0Ollama’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-server -hf datalab-to/surya-ocr-2.5-gguf:Q8_0Needs a Vulkan build of llama.cpp. Downloads the GGUF on first run.
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 datalab-to/surya-ocr-2.5-gguf:Q8_0 --host 0.0.0.0 --port 8080 -ngl 99Server and web UI on port 8080.
lms get datalab-to/surya-ocr-2.5-gguf@Q8_0Then load it from the LM Studio app or with `lms load`.
from transformers import pipeline
pipe = pipeline("image-text-to-text", model="datalab-to/surya-ocr-2.5", 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 B580 comfortably
All that fit →| Model | Params | Best quant | Memory |
|---|---|---|---|
| 716M | FP16 / BF16 | ≈2.1 GBFits in 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 | |
| 777M | FP16 / BF16 | ≈2.2 GBFits in memory | |
| 686M | FP16 / BF16 | ≈2.0 GBFits in memory |
Other GPUs that run surya-ocr-2.5
Frequently asked questions
- Can the Arc B580 run surya-ocr-2.5?
- Yes. The Arc B580 runs surya-ocr-2.5 fully in VRAM at FP16 / BF16 (about 2.0 GB of 12 GB).
- Which quantisation of surya-ocr-2.5 should I use on the Arc B580?
- 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.