Frontier model in your pocket. Powered by Bittensor SN97.
Joined October 2026
- Tweets13
- Following6
- Followers90
- Likes12
INGOT retweeted
The numbers, for anyone who wants them.
SWE-bench Multilingual 58.0 → 63.7, run-to-run noise ±2.9
Terminal-Bench 2.1 50.6 → 58.4, noise ±4.8
Both clear their noise bands, but they're single runs. Settling it takes either repeating them or a gain big enough that one run decides it.
KL is what I trust:
236 held-out agent steps, same teacher answers, paired.
0.1101 → 0.0828, 20x the measurement error.
Really proud of this one! ❤️🔥
Two weeks ago, we started Ingot's competition on Qwen3.8 27B at 1.75 bits per weight. The file is 5.95 GB instead of 54.7 GB, with a gap to the original we're working to close.
The baseline was PrismML's Ternary Bonsai 2. Since then, 27 kings have been crowned from 270 submissions. Each successive king had to bring its predictions measurably closer to the original than the preceding king's.
King XXVII's next-token predictions are 25% closer to the full-size original than Bonsai 2's on 236 held-out steps from real coding and terminal work.
SWE-bench Multilingual and Terminal-Bench both moved up for the first time this round. Those gains are right at the edge of run-to-run noise. We need more runs to see whether they hold up, so for now we call them promising, not proven.
Ingot-XXVII is still one 5.95 GB file, and the weights are open.
Download the weights: huggingface.co/dendriteholdi…
The competition continues. We'll keep testing and return with measured results and the evaluation details behind them.
INGOT retweeted
Love this kind of test: a hard, niche question you can check yourself beats any leaderboard.
Ingot was the only one to get the core idea right: every message goes to every device.
Sharper details and more speed on Mac are next. 🔥
Part 4: Ingot 27B ternary on the same MacBook (MLX 2-bit pack, not their llama.cpp fork)
19.4 tok/s, 8.4 GB. A 27B in the same memory as the 14B
Only one of the 4 to get CAN broadcast right. But it said IDs can be 8 bits and flipped its own arbitration example @ingot_wthrboss
INGOT retweeted
You read about 5 tokens a second.
A 27B model on the base M5 MacBook now writes 25.
Ternary weights, our llama.cpp fork and a DFlash drafter: 2x the usual 2-bit setup, fully offline, in 13 GB of RAM.
Try it on your Mac 👇
huggingface.co/dendriteholdi…
INGOT retweeted
Testing Ingot models locally. You can too 👇
We're tuning our fork of PrismML's llama.cpp so Ingot runs as fast as possible everywhere: NVIDIA GPUs, new Apple chips and older ones.
Here it is running on CUDA: ~250 tokens per second 👀
