gemma-4-pawarshardul-opencoder-48b-a10b-bf16

Gemma 4 Pawarshardul OpenCoder 48B-A10B BF16

Gemma 4 Pawarshardul OpenCoder 48B-A10B BF16 is a BF16 release of the OpenCoder checkpoint, post-trained for OpenCode-style software engineering workflows, long-context reasoning, and tool use.

The model has approximately 48.1B total text parameters and approximately 9.5B active text parameters per token. It supports a 262K token context window through the underlying Gemma 4 configuration.

This release is intended for high-memory serving environments that prefer BF16 weights.

Intended use

• OpenCode coding workflows
• Agentic software engineering tasks
• Long-context codebase navigation
• Reasoning-enabled tool use
• Multi-file implementation and editing sessions

Run with reasoning and tool calling enabled.

Format

• Format: BF16
• Architecture: Gemma 4
• Total text parameters: ~48.1B
• Active text parameters: ~9.5B
• Context length: 262,144 tokens
• Language focus: English

Example outputs

In OpenCode-style coding sessions, this checkpoint is intended for multi-file implementation, iterative editing, and reasoning-enabled tool use.

Serving

Use a Gemma 4 compatible runtime with reasoning and tool calling enabled.

Example:

vllm serve <repo-or-local-path> \
  --trust-remote-code \
  --reasoning-parser gemma4 \
  --tool-call-parser gemma4 \
  --enable-auto-tool-choice

For best results in OpenCode, keep the model's native chat template and enable thinking/reasoning mode.