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.

NousResearch logo

Can the RTX A6000 run Arete-27B?

Arete-27B·27.4B·RTX A6000·48 GB VRAM

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

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

QuantQualityMemoryFitSpeed
Q2_K Heavy loss13 GBfits~47 tok/s
Q3_K_M Noticeable loss15 GBfits~32 tok/s
Q4_K_M Small loss19 GBfits~25 tok/s
Q5_K_M Near-lossless23 GBfits~22 tok/s
Q6_K Near-lossless26 GBfits~19 tok/s
Q8_0 pickLossless31 GBfits~15 tok/s
FP16 / BF16 Lossless55 GBoffload~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 · Q8_0 straight from Hugging Facedocs
ollama run hf.co/bartowski/NousResearch_Arete-27B-GGUF:Q8_0
llama.cpp · OpenAI-compatible server with a web UIdocs
llama-server -hf bartowski/NousResearch_Arete-27B-GGUF:Q8_0

Downloads the GGUF on first run. Installed through llama.app? The same flags work with `llama serve`.

LM Studio · Download with the lms CLIdocs
lms get bartowski/NousResearch_Arete-27B-GGUF@Q8_0

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

vLLM · Serve an OpenAI-compatible APIdocs
vllm serve NousResearch/Arete-27B
vLLM · Smaller FP8 builddocs
vllm serve processreap/Arete-27B-FP8
vLLM · Docker Compose (NVIDIA)docs
services:
  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 an OpenAI-compatible APIdocs
sglang serve NousResearch/Arete-27B --host 0.0.0.0 --port 30000
SGLang · Docker Compose (NVIDIA)docs
services:
  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 →
ModelParamsBest quantMemorySpeedLicence
31.2BA4.6BQ8_0≈39 GBFits in memory~86 tok/sCommercial OK
20.9BA4.2BQ8_0≈13 GBFits in memory~95 tok/sCommercial OK
36BA3BQ8_0≈38 GBFits in memory~133 tok/sCommercial OK
32.8BQ8_0≈37 GBFits in memory~12 tok/sCommercial OK
30.5BA3BQ8_0≈33 GBFits in memory~133 tok/sCommercial OK
RecursiveSI logoflintRecursiveSI
39.8BA1.3BQ8_0≈43 GBFits in memory~318 tok/sCommercial OK

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.