Quantisation
46 updates on Quantisation.
Prism ML releases Ternary Bonsai, 1.58-bit models with an 8B version at 1.75 GB
Ternary Bonsai 8B needs 1.75 GB, scores 75.5 on Prism ML’s benchmark average and runs at 27 tok/s on an iPhone 17 Pro Max.
Prism ML releases 1-bit Bonsai 8B, an 8.2B-parameter model that needs 1.15 GB
1-bit Bonsai 8B stores all weights in one bit, needs 1.15 GB and runs at about 40 tok/s on an iPhone 17 Pro, according to Prism ML.
Alibaba adds 0.8B and 2B sizes to Qwen3.5, with 262K context and a vision encoder
Alibaba released Qwen3.5-0.8B and Qwen3.5-2B, dense vision-language models with a 262,144-token context, Apache 2.0 weights and 4-bit MNN builds.
Meta's MobileLLM-Pro runs a 128k context from a 590 MB 4-bit build
Meta Reality Labs released a 1.08B on-device model with a 128k context window, measured at 33.6 tok/s decode on a Galaxy S25 CPU.
Apple puts the cost of 2-bit compression at 3.4 MMLU points
Apple measures its on-device model at 67.8 MMLU in 16 bits and 64.4 after compression to 2 bits per weight, and details the distillation pipeline behind it.
Apple opens its on-device model to all apps with the Foundation Models framework
Any app can call the roughly 3-billion-parameter on-device model from Swift, offline and free of charge, with guided generation and tool calling.
Vijay Janapa Reddi argues edge generative AI needs models under 1B parameters
In ACM Queue, Vijay Janapa Reddi argues generative AI reaches edge devices only through small deployable models, with sub-1B ones the viable case.
D2MoE picks a bit-width per token, 1.39 times the throughput at up to 53 percent less memory
A MobiCom 2025 paper routes every token to an expert and a bit-width, reporting up to 1.39 times the throughput of EdgeMoE at up to 53 percent less memory.
ROMA keeps a 4-bit 3B model in on-chip ROM and reports 31,800 tok/s in synthesis
A synthesised 7 nm accelerator holds a 4-bit 3B Llama in read-only memory and the LoRA adapter in SRAM, with no chip and no FPGA prototype built.
Gemma 3 adds a 1B size that fits in 0.5 GB as an int4 checkpoint
Google released Gemma 3 at 1B, 4B, 12B and 27B with quantisation-aware int4 checkpoints of 0.5 GB and 2.6 GB for the two smallest sizes.
Raspberry Pi 5 beats human reading speed only up to Phi 3.5 mini
Helsinki and EURECOM researchers measured 11 models on a Raspberry Pi 5 and a Jetson Orin Nano, where memory and battery gave out before speed did.
MobiLLM fine-tunes OPT-1.3B in 4.5 GB on device by moving backpropagation to a server
Researchers fine-tuned OPT-1.3B on a Jetson Xavier NX in 4.5 GB by keeping the frozen model on the device and the trainable side network on a server.