PulseAugur
EN
LIVE 21:12:09

PrismML releases Bonsai 27B, enabling Qwen3.6-27B on laptops and phones

By PulseAugur Editorial · [2 sources] ·

PrismML has released Bonsai 27B, a highly compressed version of Qwen3.6-27B, available in 1-bit and ternary variants. These models are designed to run on consumer hardware like laptops and phones, with the 1-bit version requiring only 3.9GB and the ternary version 5.9GB. Despite aggressive compression, the ternary model retains approximately 94.6% of the original FP16 model's performance, while the 1-bit version maintains 89.5%, making them suitable for applications requiring large context windows and efficient memory usage. AI

IMPACT Enables running large language models on consumer devices by drastically reducing memory footprint, potentially accelerating local AI deployment.

RANK_REASON Model release from a lab (PrismML) with specific performance metrics and hardware targets. [lever_c_demoted from frontier_release: ic=2 ai=1.0]

Read on MarkTechPost →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

PrismML releases Bonsai 27B, enabling Qwen3.6-27B on laptops and phones

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Significant
Model release from a lab (PrismML) with specific performance metrics and hardware targets. [lever_c_demoted from frontier_release: ic=2 ai=1.0]
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
model release, infra
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
45 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

Full methodology in our editorial standards.

COVERAGE [2]

  1. MarkTechPost TIER_1 English(EN) · Asif Razzaq ·

    PrismML Releases Bonsai 27B: 1-bit and Ternary Builds of Qwen3.6-27B That Run on Laptops and Phones

    <p>PrismML just released Bonsai 27B. It is a low-bit representation of Qwen3.6-27B, not a new pretrain. The architecture is unchanged. Two variants ship under Apache 2.0. Ternary Bonsai 27B uses {−1, 0, +1} weights at a true 1.71 bits per weight. Its ideal size is 5.9GB. 1-bit Bo…

  2. Mastodon — fosstodon.org TIER_1 (BG) · [email protected] ·

    Qwen 3.6 27b on 8-12gb vram in llama.cpp up to 256k context 2 models prism-ml/Ternary-Bonsai-27B-gguf and prism-ml/Bonsai-27B-gguf have been released Models are presented in 2-bit

    Qwen 3.6 27b на 8-12gb vram в llama.cpp до 256к контекста Вышло 2 модели prism-ml/Ternary-Bonsai-27B-gguf и prism-ml/Bonsai-27B-gguf Модели представлены в 2-битном и 1-битном вариантах и занимают всего 7,2 и 3,8 ГБ соответственно. Но самое интересное здесь не размер, а качество п…

    LINKS habr.com/…/1059792

RELATED ENTITIES

RELATED TOPICS