Insights, research, and updates on AI acceleration technology
Our first image-generation release: quantized GGUF builds for ComfyUI and Humming builds for vLLM-Omni, generating a 1024×1024 image in roughly 8–9 seconds on a high-end GPU. Includes measured VRAM and speed for every model, setup guides for both runtimes, and 24 curated prompts compared across every variant of both families.
Read More →
A three-part series on quantized-model evaluation: does the model fit, how well does it perform, and how fast does it run on the target hardware? Why KLD measures displacement rather than direction, why BPW measures storage cost rather than realized speed, and why the quant that wins the proxies is often not the quant that wins in deployment.
Read More →
A Canada Day release: ByteShape-compressed GGUF models for Cohere North Mini Code 1.0, a Canadian coding model compressed by a Canadian team. See the best quality/speed trade-offs across RTX 4090, 5090, 4080, and 5060 Ti — pick Model 3 on 24GB+ GPUs, and Model 1 or 2 on 16GB GPUs.
Read More →
ByteShape's ShapeLearn-quantized release of Qwen 3.6 35B in NTP and MTP variants. Clear improvements across all tested hardware: pick the largest ByteShape model that fits, and on GPUs MTP adds another 20–40% token-generation throughput on top.
Read More →
ByteShape's ShapeLearn-quantized release of Qwen 3.5 35B A3B. An MoE model where CPUs are surprisingly consistent but GPUs are much pickier. See the best quality/speed trade-offs across RTX 4090, 4080, 5090, RTX Pro 6000 Blackwell, Intel i7, Ryzen 9, Ultra 7, and Raspberry Pi.
Read More →
Step-by-step guide to running a fully local, fully free AI coding agent on your own hardware. Covers LM Studio, llama.cpp, and Ollama with ByteShape GGUF models, from installation to building Flappy Bird in one prompt.
Read More →
ByteShape's ShapeLearn-quantized release of Qwen 3.5 9B. GPUs agree on the best models, CPUs have strong opinions. See the best quality/speed trade-offs across RTX 5090, 4080, 3090, 5060 Ti, Intel i7, Ryzen 9, Ultra 7, and Raspberry Pi.
Read More →
ByteShape's ShapeLearn-quantized release of Devstral-Small-2-24B and Qwen3-Coder-30B-A3B. See how we bring strong coding models to every device — from Raspberry Pi to RTX 5090 — with smaller footprints, larger context windows, and up to 50% higher quality at the same speed.
Read More →
ByteShape's device-optimized release of Qwen3-30B-A3B-Instruct-2507 showing superior TPS-quality tradeoffs across Raspberry Pi, Intel CPUs, and NVIDIA GPUs. Discover how we treat memory as a budget and optimize for what matters: speed vs. quality. Real-time performance on a Pi at 8+ TPS with 94% accuracy retention.
Read More →
We're excited to announce ByteShape's first public release of ShapeLearn-quantized models. Learn how our datatype learning technology delivers better quality at lower sizes, with benchmarks across Qwen3 4B and Llama 3.1 8B models showing superior performance on GPUs, CPUs, and Raspberry Pi.
Read More →