Baltor Get started

Models

Ling-1T

By inclusionAI. 999.7 billion parameters, a context window of 32,768 tokens and the licence mit.

Facts

Released
2025-10-02 the day the repository was first published on Hugging Face Hugging Face, read
Licence
mit 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
999.7 billion counted from the safetensors weight files Hugging Face, read
Active parameters
51.1 billion estimate estimated from the expert counts and sizes in the configuration model configuration, read
Knowledge cutoff
Unknown
Context window
  • 32,768 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

Prices in US dollars per million tokens, as each source lists them
ProviderInputOutputContextAs ofSource
ZenMux direct0.560 USD2.24 USD128,000 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
Q2_K339 GiB359 GiB367 GiB
Q2_K_L340 GiB359 GiB367 GiB
UD-Q2_K_XL342 GiB362 GiB370 GiB
Q3_K_S402 GiB425 GiB432 GiB
UD-Q3_K_XL404 GiB427 GiB434 GiB
Q3_K_M444 GiB470 GiB477 GiB
UD-Q4_K_XL525 GiB554 GiB562 GiB
Q4_0525 GiB554 GiB562 GiB
Q4_K_S528 GiB558 GiB565 GiB
Q4_K_M563 GiB594 GiB602 GiB
Q4_1583 GiB615 GiB623 GiB
Q5_K_S641 GiB676 GiB684 GiB
Q5_K_M661 GiB697 GiB705 GiB
UD-Q5_K_XL662 GiB698 GiB706 GiB
Q6_K765 GiB806 GiB813 GiB
UD-Q6_K_XL766 GiB807 GiB814 GiB
Q8_0990 GiB1,042 GiB1,050 GiB
UD-Q8_K_XL993 GiB1,046 GiB1,053 GiB
BF161,862 GiB1,959 GiB1,966 GiB

Start it with a local runtime

  • Ollama
    ollama run hf.co/unsloth/Ling-1T-GGUF:Q4_0
  • LM Studio
    lms get unsloth/Ling-1T-GGUF
lms server start
  • llama.cpp server
    llama-server -hf unsloth/Ling-1T-GGUF:Q4_0 --jinja
  • vLLM
    vllm serve inclusionAI/Ling-1T
  • SGLang
    sglang serve --model-path inclusionAI/Ling-1T --port 30000

Use it from your harness

Set up for ZenMux with the model inclusionai/ling-1t. 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": {
    "zenmux": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "ZenMux",
      "options": {
        "baseURL": "https://zenmux.ai/api/v1",
        "apiKey": "{env:ZENMUX_API_KEY}"
      },
      "models": {
        "inclusionai/ling-1t": {
          "name": "Ling-1T"
        }
      }
    }
  }
}
  • 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": {
    "zenmux": {
      "baseUrl": "https://zenmux.ai/api/v1",
      "api": "openai-completions",
      "apiKey": "$ZENMUX_API_KEY",
      "models": [
        {
          "id": "inclusionai/ling-1t"
        }
      ]
    }
  }
}
  • The apiKey field can name an environment variable as $NAME.

From Pi documentation, read .

Codex

Codex speaks only the Responses API, and ZenMux 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 ZenMux 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 .

Other ways to reach it

  • Ollama, model hf.co/unsloth/Ling-1T-GGUF:Q4_0

Published results

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