DICE Research Group

LLM API Model Catalog

Models configured for the dice-llm-api

Availability: Warm models are ready immediately. On-demand models may take a few minutes to load when first requested, and will be unload after 10min.

Model Model type Parameters Availability API test
qwen3.8-flash-next Intel/Qwen3.8-Flash-Next-W4A16-AutoRound LLM Unknown Checkpoint ID: W4A16 98,304 token context On demand
Show test cURL 
curl --request POST 'https://dice-llm-api.cs.uni-paderborn.de/v1/chat/completions' \
  --header "Authorization: Bearer ${DICE_LLM_API_KEY}" \
  --header 'Content-Type: application/json' \
  --data '{"model":"qwen3.8-flash-next","messages":[{"role":"user","content":"Reply with one short sentence confirming that the model is ready."}],"max_tokens":128,"temperature":0.2,"stream":false}'
qwen3.8-27b-fp8 Qwen/Qwen3.8-27B-FP8 LLM 27B Checkpoint ID: FP8 262,144 token context Warm
Show test cURL 
curl --request POST 'https://dice-llm-api.cs.uni-paderborn.de/v1/chat/completions' \
  --header "Authorization: Bearer ${DICE_LLM_API_KEY}" \
  --header 'Content-Type: application/json' \
  --data '{"model":"qwen3.8-27b-fp8","messages":[{"role":"user","content":"Reply with one short sentence confirming that the model is ready."}],"max_tokens":128,"temperature":0.2,"stream":false}'
gpt-oss-120b openai/gpt-oss-120b LLM 120B KV cache: FP8 131,072 token context On demand
Show test cURL 
curl --request POST 'https://dice-llm-api.cs.uni-paderborn.de/v1/chat/completions' \
  --header "Authorization: Bearer ${DICE_LLM_API_KEY}" \
  --header 'Content-Type: application/json' \
  --data '{"model":"gpt-oss-120b","messages":[{"role":"user","content":"Reply with one short sentence confirming that the model is ready."}],"max_tokens":128,"temperature":0.2,"stream":false}'
muse-glimmer-30b nvidia/Muse-Glimmer-30B-NVFP4 LLM 30B Checkpoint ID: NVFP4 131,072 token context On demand
Show test cURL 
curl --request POST 'https://dice-llm-api.cs.uni-paderborn.de/v1/chat/completions' \
  --header "Authorization: Bearer ${DICE_LLM_API_KEY}" \
  --header 'Content-Type: application/json' \
  --data '{"model":"muse-glimmer-30b","messages":[{"role":"user","content":"Reply with one short sentence confirming that the model is ready."}],"max_tokens":128,"temperature":0.2,"stream":false}'
nemotron-3.5-lightning-30b-a3b nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 LLM 30B / 3B Checkpoint ID: NVFP4 / KV cache: FP8 262,144 token context On demand
Show test cURL 
curl --request POST 'https://dice-llm-api.cs.uni-paderborn.de/v1/chat/completions' \
  --header "Authorization: Bearer ${DICE_LLM_API_KEY}" \
  --header 'Content-Type: application/json' \
  --data '{"model":"nemotron-3.5-lightning-30b-a3b","messages":[{"role":"user","content":"Reply with one short sentence confirming that the model is ready."}],"max_tokens":128,"temperature":0.2,"stream":false}'
gemma-4-31b-it google/gemma-4-31B-it-qat-w4a16-ct LLM 31B Checkpoint ID: W4A16 262,144 token context Warm
Show test cURL 
curl --request POST 'https://dice-llm-api.cs.uni-paderborn.de/v1/chat/completions' \
  --header "Authorization: Bearer ${DICE_LLM_API_KEY}" \
  --header 'Content-Type: application/json' \
  --data '{"model":"gemma-4-31b-it","messages":[{"role":"user","content":"Reply with one short sentence confirming that the model is ready."}],"max_tokens":128,"temperature":0.2,"stream":false}'
Qwen/Qwen-Image-2.1 Qwen/Qwen-Image-2.1 Image Unknown Diffusion config: FP8 Unknown Warm Unknown
google/embeddinggemma-2 google/embeddinggemma-2 Embedding Unknown Runtime dtype: BF16 8,192 token context Warm Unknown
k2-fsa/OmniVoice k2-fsa/OmniVoice TTS Unknown Unknown Unknown Warm Unknown
openai/whisper-large-v3-turbo openai/whisper-large-v3-turbo STT Unknown Runtime dtype: FP16 448 token context Warm Unknown
Qwen/Qwen3-Reranker-0.6B Qwen/Qwen3-Reranker-0.6B Reranker 0.6B Runtime dtype: BF16 4,096 token context Warm Unknown
baidu/Unlimited-OCR baidu/Unlimited-OCR OCR Unknown Runtime dtype: BF16 16,384 token context Warm Unknown