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.

FINAL-Bench logo

Can the Arc A770 16GB run Darwin-27B-RSI?

Darwin-27B-RSI·26.9B·Arc A770 16GB·16 GB VRAM

Saved in this browser, used on every model page.
Just about

Just about. At Q3_K_M it needs about 15 GB of the 16 GB available, so keep the context short, at roughly 23 tokens/s.

best quant
Q3_K_M
needs
15 GB
usable
16 GB
est. speed
~23 tok/s

Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the Darwin-27B-RSI page →

Every quantisation of Darwin-27B-RSI on the Arc A770 16GB

QuantQualityMemoryFitSpeed
Q2_K Heavy loss13 GBfits~35 tok/s
Q3_K_M pickNoticeable loss15 GBtight~23 tok/s
Q4_K_M Small loss19 GBoffload~8.2 tok/s
Q5_K_M Near-lossless23 GBoffload~4.6 tok/s
Q6_K Near-lossless26 GBoffload~3.4 tok/s
Q8_0 Lossless31 GBoffload~2.2 tok/s
FP16 / BF16 Lossless55 GBtoo big—

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 Darwin-27B-RSI on the Arc A770 16GB

Using Q3_K_M, the best fit for Arc A770 16GB.

Ollama · Q3_K_M straight from Hugging Facedocs
ollama run hf.co/bartowski/FINAL-Bench_Darwin-27B-RSI-GGUF:Q3_K_M

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 bartowski/FINAL-Bench_Darwin-27B-RSI-GGUF:Q3_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 bartowski/FINAL-Bench_Darwin-27B-RSI-GGUF:Q3_K_M --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 bartowski/FINAL-Bench_Darwin-27B-RSI-GGUF@Q3_K_M

Then load it from the LM Studio app or with `lms load`.

Transformers · Chat with the pipeline APIdocs
from transformers import pipeline

pipe = pipeline("text-generation", model="FINAL-Bench/Darwin-27B-RSI", dtype="auto", device_map="auto")
messages = [{"role": "user", "content": "Explain self-hosting in one paragraph."}]
out = pipe(messages, max_new_tokens=512)
print(out[0]["generated_text"][-1]["content"])

Chat models that fit the Arc A770 16GB comfortably

All that fit →
ModelParamsBest quantMemorySpeedLicence
20.9BA4.2BQ8_0≈13 GBFits in memory~69 tok/sCommercial OK
14.8BQ6_K≈14 GBFits in memory~25 tok/sCommercial OK
microsoft logophi-4microsoft
14.7BQ6_K≈14 GBFits in memory~26 tok/sCommercial OK
14.8BQ6_K≈14 GBFits in memory~25 tok/sCommercial OK
8.2BQ8_0≈10 GBFits in memory~35 tok/sCommercial OK
8BQ8_0≈9.8 GBFits in memory~36 tok/sConditions

Other GPUs that run Darwin-27B-RSI

Frequently asked questions

Can the Arc A770 16GB run Darwin-27B-RSI?
Just about. At Q3_K_M it needs about 15 GB of the 16 GB available, so keep the context short, at roughly 23 tokens/s.
How fast does Darwin-27B-RSI run on the Arc A770 16GB?
An estimate from memory bandwidth gives about 23 tokens/s at Q3_K_M.
Which quantisation of Darwin-27B-RSI should I use on the Arc A770 16GB?
Q3_K_M: the largest one that fits. Expected quality: noticeable 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.