Hugging Face's logo

Duckets
/
Tess-4.5-27B-Splash

Image-Text-to-Text
splash
apple-silicon
dflash2
4-bit precision
Model card Files
xet
 Community
Tess-4.5-27B-Splash / README.md
Duckets's picture
Duckets
Upload folder using huggingface_hub
6888c20 verified
preview code
|
Raw History Blame Contribute Delete
2.66 kB
metadata 
license: apache-2.0
library_name: splash
pipeline_tag: image-text-to-text
inference: false
base_model:
  - migtissera/Tess-4.5-27B
  - incoai/Qwen3.8-27B-DFlash2
tags:
  - splash
  - apple-silicon
  - dflash2
  - 4-bit

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 /v1 API defaults to greedy decoding.
  • Converted and measured by Juno for Duckets, 2026-10-19.