Can the Arc Pro B60 run Arete-27B?
Arete-27B·27.4B·Arc Pro B60·24 GB VRAM
Yes. The Arc Pro B60 runs Arete-27B fully in VRAM at Q5_K_M (about 23 GB of 24 GB), at roughly 13 tokens/s.
- best quant
- Q5_K_M
- needs
- 23 GB
- usable
- 24 GB
- est. speed
- ~13 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 Pro B60
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 13 GB | fits | ~28 tok/s |
| Q3_K_M | 15 GB | fits | ~19 tok/s |
| Q4_K_M | 19 GB | fits | ~15 tok/s |
| Q5_K_M pick | 23 GB | fits | ~13 tok/s |
| Q6_K | 26 GB | offload | ~7.9 tok/s |
| Q8_0 | 31 GB | offload | ~3.6 tok/s |
| FP16 / BF16 | 55 GB | too big | — |
Speed is a bandwidth-based estimate for generating text (456 GB/s); prompt processing and long contexts are slower.
Measured speed on the Arc Pro B60
No community reports for this pair yet.
Report your own speed →Run Arete-27B on the Arc Pro B60
Using Q5_K_M, the best fit for Arc Pro B60.
ollama run hf.co/bartowski/NousResearch_Arete-27B-GGUF:Q5_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:Q5_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:Q5_K_M --host 0.0.0.0 --port 8080 -ngl 99Server and web UI on port 8080.
lms get bartowski/NousResearch_Arete-27B-GGUF@Q5_K_MThen load it from the LM Studio app or with `lms load`.
Chat models that fit the Arc Pro B60 comfortably
All that fit →| Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|
| 20.9BA4.2B | Q8_0 | ≈13 GBFits in memory | ~56 tok/s | |
| 32.8B | Q4_K_M | ≈22 GBFits in memory | ~13 tok/s | |
| 36BA3B | Q4_K_M | ≈23 GBFits in memory | ~138 tok/s | |
| 30.5BA3B | Q5_K_M | ≈22 GBFits in memory | ~118 tok/s | |
| 24BA2B | Q6_K | ≈20 GBFits in memory | ~152 tok/s | |
| 32.8B | Q4_K_M | ≈22 GBFits in memory | ~13 tok/s |
Other GPUs that run Arete-27B
Frequently asked questions
- Can the Arc Pro B60 run Arete-27B?
- Yes. The Arc Pro B60 runs Arete-27B fully in VRAM at Q5_K_M (about 23 GB of 24 GB), at roughly 13 tokens/s.
- How fast does Arete-27B run on the Arc Pro B60?
- An estimate from memory bandwidth gives about 13 tokens/s at Q5_K_M.
- Which quantisation of Arete-27B should I use on the Arc Pro B60?
- Q5_K_M: the largest one that fits. Expected quality: near-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.