Baltor Get started

Models

bloom

By bigscience. 176.2 billion parameters, a context window of Unknown tokens and the licence bigscience-bloom-rail-1.0.

Facts

Released
2022-05-19 the day the repository was first published on Hugging Face Hugging Face, read
Licence
bigscience-bloom-rail-1.0 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
176.2 billion counted from the safetensors weight files Hugging Face, read
Active parameters
Unknown
Knowledge cutoff
Unknown
Context window
Unknown
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

No source lists a price for this model. It may only run on your own hardware.

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_K63.5 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
Q3_K_M88.0 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
Q4_K_M107 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
Q5_K_M124 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
Q6_K137 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
Q8_0178 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers

Start it with a local runtime

  • Ollama
    ollama run hf.co/DevQuasar-10/bigscience.bloom-GGUF:Q4_K_M
  • LM Studio
    lms get DevQuasar-10/bigscience.bloom-GGUF
lms server start
  • llama.cpp server
    llama-server -hf DevQuasar-10/bigscience.bloom-GGUF:Q4_K_M --jinja
  • vLLM
    vllm serve bigscience/bloom
  • SGLang
    sglang serve --model-path bigscience/bloom --port 30000

Use it from your harness

Set up for Ollama with the model hf.co/DevQuasar-10/bigscience.bloom-GGUF:Q4_K_M. 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": {
    "ollama": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Ollama",
      "options": {
        "baseURL": "http://localhost:11434/v1"
      },
      "models": {
        "hf.co/DevQuasar-10/bigscience.bloom-GGUF:Q4_K_M": {
          "name": "bloom"
        }
      }
    }
  }
}
  • 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": {
    "ollama": {
      "baseUrl": "http://localhost:11434/v1",
      "api": "openai-completions",
      "apiKey": "ollama",
      "models": [
        {
          "id": "hf.co/DevQuasar-10/bigscience.bloom-GGUF:Q4_K_M"
        }
      ]
    }
  }
}
  • The apiKey field can name an environment variable as $NAME.

From Pi documentation, read .

Codex

Put this in a terminal:

codex --oss --local-provider ollama -m hf.co/DevQuasar-10/bigscience.bloom-GGUF:Q4_K_M
  • 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="http://localhost:11434"
export ANTHROPIC_AUTH_TOKEN="ollama"
export ANTHROPIC_MODEL="hf.co/DevQuasar-10/bigscience.bloom-GGUF:Q4_K_M"
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 .

Published results

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