Unable to load
Running splash serve --model nitinpanj/Qwen3.8-27B-Splash-HQ produced the following output:
Installing nitinpanj/Qwen3.8-27B-Splash-HQ; missing artifacts will be downloaded.
manifest.json: 100%|| 13.0k/13.0k [00:00<00:00, 5.95MB/s]
manifest.json: 100%|| 13.0k/13.0k [00:00<00:00, 18.6MB/s]
error: repository is not a supported Splash runtime package
error: model download or verification failed
What have I done wrong?
Hi @napoleon-blownapart ,
Thank you for reporting this! You haven't done anything wrong—there are two reasons this occurred:
- Initial Upload in Progress: The full 27 GB model weights are actively uploading to this repository right now (~35% complete at the moment). Initially, only the tokenizer and manifest metadata were published.
- Q8 Runtime Format (
splash-packed-q8): This model is packed in the native 8-bitsplash-packed-q8(schema version 5) format with custom Metal Q8 tiled decode kernels. Official upstream Splash 1.0 (incoai/splash) only has 4-bit schemas (splash-packed-q4, schema 3/4) hardcoded in its package validator, which causes it to reject schema 5 as an unsupported runtime package.
To run this model once the weight files finish streaming:
- Use the Q8-enabled Splash runtime fork documented here:
👉 https://github.com/npanj/qwen3.8-27b-apple-silicon-eval
We've updated the model card on this repo with the engine requirements and real-time status. The upload should finish within ~1.5 hours!
Ok, cheers.
Two questions:
- Will that fork also run the Q8 quant Qwen3.6 model?
- Can I run the Q4 quant models from this fork or do I need to use the one I installed using
brew install incoai/tap/splash?
Hi @napoleon-blownapart ,
Good questions!
- Q8 on Qwen3.6: Not currently. Qwen3.6 is an MoE architecture (
splash-packed-q4-moe, 256 experts routed per token, schema 4 /MDFM0001). The Q8 Metal tiled kernels and packaging format (splash-packed-q8/MDFL0008) in this fork were built specifically for dense models (Qwen3.8's 64 dense layers). A Q8 MoE kernel would need custom tiled dequantization for the routed expert blocks, which hasn't been implemented yet. - Backwards compatibility with Q4: Yes, 100%. The fork is a strict superset of upstream Splash. All original 4-bit dense and MoE schemas (
splash-packed-q4,splash-packed-q4-moe) and compiled Metal kernels remain fully intact. You can serve official models (likeincoai/Qwen3.8-27B-Splashorincoai/Qwen3.6-35B-A3B-Splash) directly with this fork without needing to switch back to the Homebrew version.