Tess-4.5-27B for Splash
A Splash package of Tess-4.5-27B, a Qwen3.8-27B fine-tune, for LM Studio's Splash runtime on Apple silicon.
Credit
- The model: Tess-4.5-27B by migtissera. This package is only a re-packaging of their fine-tune into Splash format — all credit for the model itself goes to them. None of this would exist without their work.
- Splash engine, and the official Qwen3.8-27B Splash package this conversion reuses the DFlash 2 draft and vision tower from: Inco AI.
- Conversion tooling: publicExcess/splash-converter.
Converted from the BF16 checkpoint (revision
91b231133470bd147aac8036ed94d35e9bf1dc13) with the community
splash-converter.
The DFlash 2 draft and the vision tower are reused from Inco AI's
official Qwen3.8-27B Splash package — the draft is the standard
Qwen3.8-27B one, not retrained for this fine-tune. Package format:
splash-packed-q4, schema 3, 78 artifacts, ~17.4 GB.
Measured speed
Mac Studio, Apple M5 Max, 128 GB. Identical ~60-token prompt, temperature 0, 1,000 max tokens, one model resident at a time, decode tok/s excluding prefill:
| Host | Decode tok/s |
|---|---|
| Tess-4.5-27B, this package in LM Studio | 77.6 |
| Qwen3.8-27B, official package in LM Studio | 79.5 |
| Tess-4.5-27B, standalone Splash server (MLX build) | 60.4 |
| Tess-4.5-27B, MLX in LM Studio | 33.0 |
Use with LM Studio
Requires an M3 or newer Mac, macOS 26.4 or later, 36 GB memory minimum (48 GB+ recommended) and the Splash runtime (Settings → Runtime). Download this repo into your LM Studio models folder; it is cataloged as a Splash model and loads on the Splash engine.
Use with the standalone server
Current standalone Splash loads MLX checkpoints directly and no longer loads packages. Serve the MLX build instead:
brew install incoai/tap/splash
splash serve --model juno/Tess-4.5-27B-MLX-4bit
Notes
- The package carries no
generation_config.json(the format has nowhere to put it); set sampling in your client. The/v1API defaults to greedy decoding. - Converted and measured by Juno for Duckets, 2026-10-19.