Baltor Get started

Models

NVIDIA-Nemotron-Nano-9B-v2

By nvidia. 8.9 billion parameters, a context window of 131,072 tokens and the licence other.

Facts

Released
2025-08-12 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
8.9 billion counted from the safetensors weight files Hugging Face, read
Active parameters
Unknown
Knowledge cutoff
Unknown
Context window
  • 131,072 tokens the maximum position embeddings in the model configuration model configuration, read
Longest output
Unknown
Tool calling
  • Yes the chat template in the tokenizer configuration accepts tool definitions Hugging Face, read
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
Nvidia0 USD0 USD131,072 older than 30 days; check the providermodels.dev, read
Deep Infra0.040 USD0.160 USD131,072LiteLLM, read
Together AI0.060 USD0.250 USD131,072LiteLLM, 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
IQ3_XXS4.7 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
IQ3_XS4.8 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
Q3_K_S4.8 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
IQ3_M4.9 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
IQ4_XS4.9 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
IQ4_NL4.9 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
Q4_05.0 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
Q3_K_M5.0 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
Q4_15.4 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
Q4_K_S5.8 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
Q4_K_M6.1 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
Q5_K_S6.3 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
Q5_K_M6.6 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
Q5_K_L6.8 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
Q8_08.8 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
BF1616.6 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers

Start it with a local runtime

  • Ollama
    ollama run hf.co/bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF:Q4_0
  • LM Studio
    lms get bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF
    lms server start
  • llama.cpp server
    llama-server -hf bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF:Q4_0 --jinja
  • vLLM
    vllm serve nvidia/NVIDIA-Nemotron-Nano-9B-v2
  • SGLang
    sglang serve --model-path nvidia/NVIDIA-Nemotron-Nano-9B-v2 --port 30000

Use it from your harness

Set up for DeepInfra with the model nvidia/NVIDIA-Nemotron-Nano-9B-v2. 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": {
    "deepinfra": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "DeepInfra",
      "options": {
        "baseURL": "https://api.deepinfra.com/v1/openai",
        "apiKey": "{env:DEEPINFRA_TOKEN}"
      },
      "models": {
        "nvidia/NVIDIA-Nemotron-Nano-9B-v2": {
          "name": "NVIDIA-Nemotron-Nano-9B-v2"
        }
      }
    }
  }
}
  • 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": {
    "deepinfra": {
      "baseUrl": "https://api.deepinfra.com/v1/openai",
      "api": "openai-completions",
      "apiKey": "$DEEPINFRA_TOKEN",
      "models": [
        {
          "id": "nvidia/NVIDIA-Nemotron-Nano-9B-v2"
        }
      ]
    }
  }
}
  • The apiKey field can name an environment variable as $NAME.

From Pi documentation, read .

Codex

Codex speaks only the Responses API, and DeepInfra 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

Put this in ~/.claude/settings.json, or variables in your shell:

export ANTHROPIC_BASE_URL="https://api.deepinfra.com/anthropic"
export ANTHROPIC_AUTH_TOKEN="$DEEPINFRA_TOKEN"
export ANTHROPIC_MODEL="nvidia/NVIDIA-Nemotron-Nano-9B-v2"
claude
  • 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 .

Other ways to reach it

  • Nvidia, model nvidia/nvidia-nemotron-nano-9b-v2
  • Together AI, model nvidia/NVIDIA-Nemotron-Nano-9B-v2
  • Ollama, model hf.co/bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF:Q4_0

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.