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.

inclusionAI logo

Can the Arc A770 16GB run ZwZ2-4B?

ZwZ2-4B·4.5B·Arc A770 16GB·16 GB VRAM

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

Yes. The Arc A770 16GB runs ZwZ2-4B fully in VRAM at FP16 / BF16 (about 9.7 GB of 16 GB), at roughly 34 tokens/s.

best quant
FP16 / BF16
needs
9.7 GB
usable
16 GB
est. speed
~34 tok/s

Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the ZwZ2-4B page →

Every quantisation of ZwZ2-4B on the Arc A770 16GB

QuantQualityMemoryFitSpeed
Q2_K Heavy loss3.2 GBfits~206 tok/s
Q3_K_M Noticeable loss3.5 GBfits~139 tok/s
Q4_K_M Small loss4.2 GBfits~112 tok/s
Q5_K_M Near-lossless4.7 GBfits~95 tok/s
Q6_K Near-lossless5.1 GBfits~82 tok/s
Q8_0 Lossless5.9 GBfits~64 tok/s
FP16 / BF16 pickLossless9.7 GBfits~34 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 ZwZ2-4B on the Arc A770 16GB

Using FP16 / BF16, the best fit for Arc A770 16GB.

Ollama · F16 straight from Hugging Facedocs
ollama run hf.co/inclusionAI/ZwZ2-4B-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 inclusionAI/ZwZ2-4B-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 inclusionAI/ZwZ2-4B-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 inclusionAI/ZwZ2-4B-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="inclusionAI/ZwZ2-4B", 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"])

Vision models that fit the Arc A770 16GB comfortably

All that fit →
ModelParamsBest quantMemorySpeedLicence
4.7BQ8_0≈5.9 GBFits in memory~62 tok/sCommercial OK
4.3BQ8_0≈5.2 GBFits in memory~67 tok/sConditions
4.4BQ8_0≈5.8 GBFits in memory~65 tok/sCommercial OK
4.3BQ8_0≈5.6 GBFits in memory~67 tok/sConditions
3.8BQ8_0≈4.0 GBFits in memory~77 tok/sNon-commercial
5BQ8_0≈5.6 GBFits in memory~58 tok/sConditions

Other GPUs that run ZwZ2-4B

Frequently asked questions

Can the Arc A770 16GB run ZwZ2-4B?
Yes. The Arc A770 16GB runs ZwZ2-4B fully in VRAM at FP16 / BF16 (about 9.7 GB of 16 GB), at roughly 34 tokens/s.
How fast does ZwZ2-4B run on the Arc A770 16GB?
An estimate from memory bandwidth gives about 34 tokens/s at FP16 / BF16.
Which quantisation of ZwZ2-4B should I use on the Arc A770 16GB?
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.