Can the Arc A770 16GB run WeVisCut?
WeVisCut·9.4B·Arc A770 16GB·16 GB VRAM
Yes. The Arc A770 16GB runs WeVisCut fully in VRAM at Q8_0 (about 11 GB of 16 GB), at roughly 31 tokens/s.
- best quant
- Q8_0
- needs
- 11 GB
- usable
- 16 GB
- est. speed
- ~31 tok/s
Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the WeVisCut page →
Every quantisation of WeVisCut on the Arc A770 16GB
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 4.5 GB | fits | ~100 tok/s |
| Q3_K_M | 6.0 GB | fits | ~67 tok/s |
| Q4_K_M | 7.0 GB | fits | ~54 tok/s |
| Q5_K_M | 7.8 GB | fits | ~46 tok/s |
| Q6_K | 8.7 GB | fits | ~40 tok/s |
| Q8_0 pick | 11 GB | fits | ~31 tok/s |
| FP16 / BF16 | 19 GB | offload | ~7 tok/s |
Speed is a bandwidth-based estimate for generating text (560 GB/s); prompt processing and long contexts are slower.
Measured speed on the Arc A770 16GB
No community reports for this pair yet.
Report your own speed →Run WeVisCut on the Arc A770 16GB
Using Q8_0, the best fit for Arc A770 16GB.
llama-server -hf prithivMLmods/tencent-WeVisCut-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 prithivMLmods/tencent-WeVisCut-GGUF:Q8_0 --host 0.0.0.0 --port 8080 -ngl 99Server and web UI on port 8080.
Omni models that fit the Arc A770 16GB comfortably
All that fit →| Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|
| 9.4B | Q8_0 | ≈10 GBFits in memory | ~31 tok/s | |
| 8B | Q8_0 | ≈9.2 GBFits in memory | ~36 tok/s | |
| 10.7B | Q8_0 | ≈8.9 GBFits in memory | ~27 tok/s | |
| 9.1B | Q8_0 | ≈10 GBFits in memory | ~32 tok/s | |
| 12B | Q6_K | ≈13 GBFits in memory | ~31 tok/s | |
| 8.3B | Q8_0 | ≈10 GBFits in memory | ~35 tok/s |
Other GPUs that run WeVisCut
Frequently asked questions
- Can the Arc A770 16GB run WeVisCut?
- Yes. The Arc A770 16GB runs WeVisCut fully in VRAM at Q8_0 (about 11 GB of 16 GB), at roughly 31 tokens/s.
- How fast does WeVisCut run on the Arc A770 16GB?
- An estimate from memory bandwidth gives about 31 tokens/s at Q8_0.
- Which quantisation of WeVisCut should I use on the Arc A770 16GB?
- Q8_0: 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.