Can the Arc A770 16GB run Arete-27B?
Arete-27B·27.4B·Arc A770 16GB·16 GB VRAM
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 Arete-27B page →
Every quantisation of Arete-27B on the Arc A770 16GB
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 13 GB | fits | ~34 tok/s |
| Q3_K_M pick | 15 GB | tight | ~23 tok/s |
| Q4_K_M | 19 GB | offload | ~7.6 tok/s |
| Q5_K_M | 23 GB | offload | ~4.6 tok/s |
| Q6_K | 26 GB | offload | ~3.3 tok/s |
| Q8_0 | 31 GB | offload | ~2.1 tok/s |
| FP16 / BF16 | 55 GB | too 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 Arete-27B on the Arc A770 16GB
Using Q3_K_M, the best fit for Arc A770 16GB.
ollama run hf.co/bartowski/NousResearch_Arete-27B-GGUF:Q3_K_MOllama’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 bartowski/NousResearch_Arete-27B-GGUF:Q3_K_MNeeds 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 bartowski/NousResearch_Arete-27B-GGUF:Q3_K_M --host 0.0.0.0 --port 8080 -ngl 99Server and web UI on port 8080.
lms get bartowski/NousResearch_Arete-27B-GGUF@Q3_K_MThen load it from the LM Studio app or with `lms load`.
Chat models that fit the Arc A770 16GB comfortably
All that fit →| Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|
| 20.9BA4.2B | Q8_0 | ≈13 GBFits in memory | ~69 tok/s | |
| 14.8B | Q6_K | ≈14 GBFits in memory | ~25 tok/s | |
| 14.7B | Q6_K | ≈14 GBFits in memory | ~26 tok/s | |
| 14.8B | Q6_K | ≈14 GBFits in memory | ~25 tok/s | |
| 8.2B | Q8_0 | ≈10 GBFits in memory | ~35 tok/s | |
| 8B | Q8_0 | ≈9.8 GBFits in memory | ~36 tok/s |
Other GPUs that run Arete-27B
Frequently asked questions
- Can the Arc A770 16GB run Arete-27B?
- 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 Arete-27B run on the Arc A770 16GB?
- An estimate from memory bandwidth gives about 23 tokens/s at Q3_K_M.
- Which quantisation of Arete-27B 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.