Qwen3.8-27B-oQ4e-MTP-MLX

Qwen3.8-27B-oQ4e-MTP-MLX

This is the Qwen3.8-27B model package used by Sprig in Treeish. It combines an oQ4e mixed-precision MLX quant with its embedded Multi-Token Prediction head and the chat template used for Sprig's coding-agent workflow.

The package is ready to download and load as-is. Treeish pins an exact repository commit rather than following main.

Model

• Base model: Qwen/Qwen3.8-27B
• Architecture: 27B dense parameters
• Quantisation: oQ4e imatrix-enhanced mixed precision
• Default quantisation: 4-bit affine, group size 64
• Per-tensor overrides: 5-bit, with group size 64
• Format: MLX safetensors
• MTP: 1 embedded layer under language_model.mtp.*
• Context length: 262,144 tokens

The package contains 2,209 indexed tensors, including 333 vision-tower tensors and 29 embedded MTP tensors. Its 4 weight shards contain 16,971,681,558 bytes of tensor data.

Provenance

The quantised weights, model configuration and oQ calibration report are byte-identical to Jundot/Qwen3.8-27B-oQ4e-mtp at commit 04dc5509edd8670fc78cc8c2f74bf9b77b1f2acc. The source declares oMLX 0.6.1 as the converter and Qwen/Qwen3.8-27B as the base model. Its imatrix report records 128 samples of 512 tokens from oqe_code_multilingual, with 503 of 504 entries applied. It does not identify the exact base-model commit used for conversion, so this is a curated, byte-pinned distribution rather than a byte-reproducible conversion recipe.

The chat template is Froggeric's v22.5 template. It is byte-identical to chat_template.jinja in froggeric/Qwen-Fixed-Chat-Templates at commit 855bffc49448e299789730ff92c9b8d834d6cc14.

No model, tokenizer or configuration tensors were changed for this release. The release replaces the chat template and adds the licence, provenance and file manifest.

Runtime compatibility

This package is built for Treeish's pinned MLX Swift runtime. A different runtime must support the per-tensor quantisation overrides in config.json and the embedded Qwen MTP layout.

Treeish uses this model from 48 GB of unified memory and recommends 64 GB. Headroom depends on context length, cache settings and other running applications.

Treeish validation

Treeish's release benchmark has not yet been run on this package. RELEASE_MANIFEST.json records the release status and is updated when it has.

Limitations

Quantisation trades some model quality for memory use and local generation speed. Applications should validate the model against their own prompts, tool format and runtime.

The model package contains no custom executable code. File sizes, SHA-256 digests and source revisions are recorded in RELEASE_MANIFEST.json.

Licence

Qwen3.8-27B is licensed under Apache 2.0. The full licence text is included in LICENSE. The Froggeric template repository also declares Apache 2.0 and is attributed above.