Baltor Get started

Models

NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16

By nvidia. 560.5 billion parameters, a context window of 262,144 tokens and the licence other.

Facts

Released
2026-06-03 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
560.5 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
Pioneer0.500 USD2.50 USD1,000,000 older than 30 days; check the providermodels.dev, 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
UD-IQ1_M175 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
UD-IQ2_XXS181 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
UD-IQ2_M181 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
UD-Q2_K_XL188 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
UD-IQ3_XXS208 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
UD-IQ3_S233 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
UD-Q3_K_M255 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
UD-Q3_K_XL255 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
UD-IQ4_XS266 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
UD-IQ4_NL274 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
UD-Q4_K_S305 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
MXFP4_MOE328 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
UD-Q4_K_M335 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
UD-Q4_K_XL335 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
UD-Q5_K_S365 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
UD-Q5_K_M397 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
UD-Q5_K_XL398 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
UD-Q6_K429 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
UD-Q6_K_XL487 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
Q8_0544 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
UD-Q8_K_XL554 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
BF161,024 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers

Start it with a local runtime

  • Ollama
    ollama run hf.co/unsloth/NVIDIA-Nemotron-3-Ultra-550B-A55B-GGUF:UD-IQ1_M
  • LM Studio
    lms get unsloth/NVIDIA-Nemotron-3-Ultra-550B-A55B-GGUF
    lms server start
  • llama.cpp server
    llama-server -hf unsloth/NVIDIA-Nemotron-3-Ultra-550B-A55B-GGUF:UD-IQ1_M --jinja
  • vLLM
    vllm serve nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
  • SGLang
    sglang serve --model-path nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 --port 30000

Use it from your harness

Set up for Pioneer with the model nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16. Each endpoint page has the same setup for its own address.

OpenCode

Put this in opencode.json in your project folder:

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "pioneer": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Pioneer",
      "options": {
        "baseURL": "https://api.fastino.ai/v1",
        "apiKey": "{env:PIONEER_API_KEY}"
      },
      "models": {
        "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16": {
          "name": "NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16"
        }
      }
    }
  }
}
  • OpenCode reads any OpenAI-compatible address through the @ai-sdk/openai-compatible package, and an address that speaks the Responses API through @ai-sdk/openai.

From OpenCode documentation, read .

Pi

Put this in ~/.pi/agent/models.json:

{
  "providers": {
    "pioneer": {
      "baseUrl": "https://api.fastino.ai/v1",
      "api": "openai-completions",
      "apiKey": "$PIONEER_API_KEY",
      "models": [
        {
          "id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16"
        }
      ]
    }
  }
}
  • The apiKey field can name an environment variable as $NAME.

From Pi documentation, read .

Codex

Codex speaks only the Responses API, and Pioneer documents no Responses address. A gateway that offers one can sit in between.

  • Codex speaks the Responses API only: responses is the one supported wire API of a custom provider. Ollama and LM Studio are built in and start with --oss.

From Codex documentation, read .

Claude Code

Claude Code sends Anthropic Messages requests, and Pioneer documents no such address. A gateway that translates to that API can sit in between.

  • Claude Code sends Anthropic Messages requests to ANTHROPIC_BASE_URL. Anthropic says it does not support routing Claude Code to models other than Claude through any gateway, so some features may not work with another model.

From Claude Code documentation, read .

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.