Qwen3.6-35B-go-v2-MTP-bf16.mlx

Qwen3.6-35B-go-v2 MTP BF16 MLX

A Go-focused Qwen3.6-35B-A3B model for Apple Silicon, packaged in MLX with native MTP enabled.

Use it as a coding assistant for Go projects: generating focused patches, explaining diffs, tightening tests, reading tool outputs, and making small repo-aware edits. It was tested with Swival on file-editing and command-running workflows.

This is the BF16 full-precision native-MTP variant. Use it when quality and full precision matter more than disk and memory footprint.

Which Variant Should I Use?

• Use this repo if your runtime supports native MTP for this Qwen3.5 MoE MLX layout and you want the full-precision package.
• Use jedisct1/Qwen3.6-35B-go-v2-MTP-4bit.mlx if you want the smallest and fastest MTP variant.
• Use jedisct1/Qwen3.6-35B-go-v2-MTP-8bit.mlx if you want a quantized MTP model with more precision than 4-bit.
• Use jedisct1/Qwen3.6-35B-go-v2-bf16.mlx if your loader does not support native MTP sidecars.

What It Is Good At

• Writing idiomatic Go patches from a concise change request.
• Explaining Go diffs in commit-message style.
• Following tool-calling workflows where it needs to inspect files before editing.
• Keeping changes focused instead of turning small fixes into broad rewrites.
• Working with tests, command output, and repository context.

Example Prompts

Generate a patch:

You are an expert Go developer.

Generate a focused patch for this change:

Replace the manual retry loop in fetchUser() with the shared retry helper, and add a regression test for a transient 503.

Explain a change:

You are an expert Go developer.

Describe what this Go diff changes and call out any behavior change:

<paste a Go diff here>

Use tools:

Inspect the repository, find where request timeouts are configured, update the Go code to use the new default, and run the relevant tests.

Compatibility

This repo intentionally keeps native MTP weights. If your loader rejects language_model.mtp.* tensors or mtp.safetensors, use the plain BF16 sibling instead:

jedisct1/Qwen3.6-35B-go-v2-bf16.mlx

Limitations

• Outputs should be reviewed before use, especially patches that touch production systems.
• The model works best on focused Go changes, tests, and explanations. Very large refactors may need to be split into smaller steps.
• Tool calling depends on the runtime and client preserving the chat template and tool schema format.