FrontiersMind/Lumma-fev-27B-GGUF

Lumma-Fev-27B is a decision model. You give it a state (text) and typed questions; it returns a probability for every option in one forward pass. It never generates text, so there is nothing to parse. It works in English, Hindi, Tamil and Kannada, and was trained on about 100K samples. It is a full-weight fine-tune of Qwen3.8-27B.

📖 Read the detailed blog: https://huggingface.co/blog/FrontiersMind/lumma-fev-27b

Results (accuracy, same rows for both models)

English Benchmarks

Indic Benchmarks

Use it

The easiest way is the lumma-fev package, the same one that runs every other Lumma-Fev size. You need a GPU with about 55 GB free (an 80 GB card), or several smaller GPUs with device_map="auto".

pip install "lumma-fev>=0.2"

import lumma_fev

model = lumma_fev.load("FrontiersMind/Lumma-fev-27B")          # or lumma_fev.load("27b")
# model = lumma_fev.load("27b", device_map="auto")             # several GPUs: pip install "lumma-fev[large]"

answers = model.decide(
    state="My integration keeps failing. Please help.",
    questions={
        "team": {
            "type": "choice",
            "instructions": "Which team should handle this request?",
            "criteria": {
                "billing": "Charges and refunds",
                "support": "Technical integration errors",
                "sales": "Questions about buying a product",
            },
        },
        "urgent": {"type": "noul", "instructions": "Does the customer need a reply today?"},
    },
)
print(answers["team"])
# {"type": "choice", "choice": "support", "confidence": 0.99..., "probabilities": {"billing": ..., "support": ..., "sales": ...}}

state can be text, a JSON object or an array. Each question reads the state and its own options only, so one answer never changes another. Images: pass images=[...] (paths, PIL images or data: URLs) after pip install "lumma-fev[images]". A question plus the state must fit in 8,192 tokens. The model was trained on noul and choice questions; score questions are accepted but untested.

To serve it behind the TypeSafe-compatible POST /v1/systemone API:

pip install "lumma-fev[serve]"
lumma-fev-serve --model 27b --host 0.0.0.0 --port 8000          # add --device-map auto for several GPUs

For speed, also install the flash-linear-attention and causal-conv1d kernels; without them transformers uses slower PyTorch code.