No official torrent yet — requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from ConwayResearch/Underdog-Ternary-1.1
All models by ConwayResearch →DEPRICATED: This model, based on Ternary Bonsai 2 27B is no longer being served to underdog users as it is not performant per user feedback. We found the base model to be optimized for benchmarks vs usable for users. Please choose another model from the dozens that are available.
Underdog-Ternary by Conway is a 27-billion-parameter assistant for conversation, writing, coding, and summarization. This release combines post training with compact ternary weights for local inference. We applied post training to this model to run better in Underdog for human users, based on Bonsai 2.
Choose GGUF for accelerated generation with Splash, or the MLX package for native Apple Silicon workflows.
On an Apple M5 Max, Splash with DFlash2 delivered up to 157.9 generated tokens per second in our coding test.
Measured on Apple M5 Max with 40 GPU cores and 48 GiB unified memory. Both configurations use the same checkpoint in their respective MLX and GGUF packages. Values are means of two runs per task with temperature 0, thinking disabled, a 512-token output limit, and no reused prompt prefix. Engines were measured separately. Input lengths were 43, 44, and 3,003 tokens; generated output lengths may differ. Model loading and warmup are excluded. Splash 1.1.0 uses DFlash2 and INT8 KV; MLX 0.32.0 / MLX-LM 0.31.3 uses the bundled Hadamard-aware runtime without a draft model. The table reports generation throughput.
On an Apple Silicon Mac, install Splash 1.1.0 or later, then run:
The explicit :PQ2_0 selector selects the GGUF; Splash prepares its compatible draft model automatically. Open the chat page shown by the service, or connect your application through its OpenAI-compatible API. For medium thinking in the chat page, select Medium in the thinking menu.
The ternary GGUF (PQ2_0) runs on PrismML's llama.cpp build. Download its latest Windows CUDA release from the releases page (llama-prism-*-bin-win-cuda-*-x64.zip and the matching cudart-llama-bin-win-cuda-*-x64.zip, extracted into one folder). Then download the GGUF from this repository and the DFlash2 draft model:
Download only the variant used by your application. Keep the MLX configuration, tokenizer, chat template, and runtime together with its weights.
For Python integration, the supplied MLX runtime exposes vision_artifact.load_vl_model; use load_processor=False for text inference.
splash serve \ --model ConwayResearch/Underdog-Ternary-1.1:PQ2_0 \ --language-only \ --default-reasoning-effort mediumhf download ConwayResearch/Underdog-Ternary-1.1 Underdog-PQ2_0.gguf --local-dir ./underdog-2bithf download incoai/Qwen3.8-27B-DFlash2-GGUF Qwen3.8-27B-DFlash2-Q8_0.gguf --local-dir ./underdog-2bitllama-server.exe -m .\underdog-2bit\Underdog-PQ2_0.gguf ` -md .\underdog-2bit\Qwen3.8-27B-DFlash2-Q8_0.gguf ` --spec-type draft-dflash --spec-draft-n-max 3 ` -ngl 99 -ngld 99 -fa on -c 16384 --jinjahf download ConwayResearch/Underdog-Ternary-1.1 \ --include "mlx/*" --include "LICENSE" \ --local-dir ./underdog-2bit