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.

tencent logo

Can the Arc A770 16GB run WeVisCut?

WeVisCut·9.4B·Arc A770 16GB·16 GB VRAM

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

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

QuantQualityMemoryFitSpeed
Q2_K Heavy loss4.5 GBfits~100 tok/s
Q3_K_M Noticeable loss6.0 GBfits~67 tok/s
Q4_K_M Small loss7.0 GBfits~54 tok/s
Q5_K_M Near-lossless7.8 GBfits~46 tok/s
Q6_K Near-lossless8.7 GBfits~40 tok/s
Q8_0 pickLossless11 GBfits~31 tok/s
FP16 / BF16 Lossless19 GBoffload~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.cpp · OpenAI-compatible server with a web UIdocs
llama-server -hf prithivMLmods/tencent-WeVisCut-GGUF:Q8_0

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 prithivMLmods/tencent-WeVisCut-GGUF:Q8_0 --host 0.0.0.0 --port 8080 -ngl 99

Server and web UI on port 8080.

Omni models that fit the Arc A770 16GB comfortably

All that fit →
ModelParamsBest quantMemorySpeedLicence
9.4BQ8_0≈10 GBFits in memory~31 tok/sCommercial OK
8BQ8_0≈9.2 GBFits in memory~36 tok/sCommercial OK
10.7BQ8_0≈8.9 GBFits in memory~27 tok/sCommercial OK
9.1BQ8_0≈10 GBFits in memory~32 tok/sCommercial OK
12BQ6_K≈13 GBFits in memory~31 tok/sCommercial OK
8.3BQ8_0≈10 GBFits in memory~35 tok/sCheck licence

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.