Yes. The RTX A6000 runs Arete-27B fully in VRAM at Q8_0 (about 31 GB of 48 GB), at roughly 15 tokens/s.
- best quant
- Q8_0
- needs
- 31 GB
- usable
- 48 GB
- est. speed
- ~15 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 RTX A6000
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 13 GB | fits | ~47 tok/s |
| Q3_K_M | 15 GB | fits | ~32 tok/s |
| Q4_K_M | 19 GB | fits | ~25 tok/s |
| Q5_K_M | 23 GB | fits | ~22 tok/s |
| Q6_K | 26 GB | fits | ~19 tok/s |
| Q8_0 pick | 31 GB | fits | ~15 tok/s |
| FP16 / BF16 | 55 GB | offload | ~3.1 tok/s |
Speed is a bandwidth-based estimate for generating text (768 GB/s); prompt processing and long contexts are slower.
Measured speed on the RTX A6000
No community reports for this pair yet.
Report your own speed →Run Arete-27B on the RTX A6000
Using Q8_0, the best fit for RTX A6000.
ollama run hf.co/bartowski/NousResearch_Arete-27B-GGUF:Q8_0 llama-server -hf bartowski/NousResearch_Arete-27B-GGUF:Q8_0Downloads the GGUF on first run. Installed through llama.app? The same flags work with `llama serve`.
lms get bartowski/NousResearch_Arete-27B-GGUF@Q8_0Then load it from the LM Studio app or with `lms load`.
vllm serve NousResearch/Arete-27B vllm serve processreap/Arete-27B-FP8services:
vllm:
image: vllm/vllm-openai:latest
command: NousResearch/Arete-27B
ports:
- "8000:8000"
ipc: host
volumes:
- ~/.cache/huggingface:/root/.cache/huggingface
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: all
capabilities: [gpu]API on port 8000.
sglang serve NousResearch/Arete-27B --host 0.0.0.0 --port 30000services:
sglang:
image: lmsysorg/sglang:latest
command: sglang serve NousResearch/Arete-27B --host 0.0.0.0 --port 30000
ports:
- "30000:30000"
ipc: host
volumes:
- ~/.cache/huggingface:/root/.cache/huggingface
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: all
capabilities: [gpu]API on port 30000.
Chat models that fit the RTX A6000 comfortably
All that fit →| Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|
| 31.2BA4.6B | Q8_0 | ≈39 GBFits in memory | ~86 tok/s | |
| 20.9BA4.2B | Q8_0 | ≈13 GBFits in memory | ~95 tok/s | |
| 36BA3B | Q8_0 | ≈38 GBFits in memory | ~133 tok/s | |
| 32.8B | Q8_0 | ≈37 GBFits in memory | ~12 tok/s | |
| 30.5BA3B | Q8_0 | ≈33 GBFits in memory | ~133 tok/s | |
| 39.8BA1.3B | Q8_0 | ≈43 GBFits in memory | ~318 tok/s |
Other GPUs that run Arete-27B
Frequently asked questions
- Can the RTX A6000 run Arete-27B?
- Yes. The RTX A6000 runs Arete-27B fully in VRAM at Q8_0 (about 31 GB of 48 GB), at roughly 15 tokens/s.
- How fast does Arete-27B run on the RTX A6000?
- An estimate from memory bandwidth gives about 15 tokens/s at Q8_0.
- Which quantisation of Arete-27B should I use on the RTX A6000?
- 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.