Baltor Get started

Models

Gemma-4-31B-IT-NVFP4

By nvidia. 20.9 billion parameters, a context window of 262,144 tokens and the licence other.

Facts

Released
2026-04-02 the day the repository was first published on Hugging Face Hugging Face, read
Licence
other the licence the model card declares Hugging Face, read
Open weights
Yes the weights are published in this Hugging Face repository Hugging Face, read
Parameters
20.9 billion counted from the safetensors weight files Hugging Face, read
Active parameters
Unknown
Knowledge cutoff
Unknown
Context window
  • 262,144 tokens the maximum position embeddings in the model configuration model configuration, read
Longest output
Unknown
Tool calling
Unknown
Structured output
Unknown
Reasoning controls
Unknown
Inputs and outputs
text in, text out Hugging Face, read
Good for
No source names a use.

Prices

Each provider's own price in US dollars per million tokens, as an openly licensed source lists it
ProviderInputOutputContextAs ofSource
sail0.140 USD0.400 USD262,144LiteLLM, read

Run it on your own hardware

Weights are the sizes of the files a source lists, or an estimate from the parameter count where none does. Memory is an estimate: weights plus KV cache plus 512 MiB and 5 percent of the weights for runtime buffers. Check it against your hardware.

QuantizationWeightsMemory at 8,192 tokensMemory at 32,768 tokens
F16 estimate38.9 GiB48.8 GiB71.3 GiB
Q8_0 estimate20.7 GiB29.7 GiB52.2 GiB
Q4_0 estimate10.9 GiB19.5 GiB42.0 GiB

Start it with a local runtime

  • vLLM
    vllm serve nvidia/Gemma-4-31B-IT-NVFP4
  • SGLang
    sglang serve --model-path nvidia/Gemma-4-31B-IT-NVFP4 --port 30000

Use it from your harness

No endpoint in this directory serves this model yet.

Published results

These are results other people published. Baltor did not run them and does not rank models by them.

Two more publishers are linked, never copied, because their terms do not allow it:

  • Artificial Analysis publishes its own intelligence, speed and price measurements.
  • OpenRouter lists current prices and uptime for each provider it routes to.