VIDRAFT's POCKET 35B model runs on phones and PCs without GPUs

By PulseAugur Editorial · [1 sources] · 2026-07-23 05:17

VIDRAFT has released POCKET, a 35 billion parameter Mixture-of-Experts model that can run on devices without GPUs, including PCs and phones, using standard tools like llama.cpp. This offers an alternative to models like Bonsai, which require more powerful hardware for comparable performance. POCKET's sparse architecture allows it to be faster than denser models of similar or even larger sizes in many on-device scenarios, prioritizing privacy and reproducibility by running entirely locally. AI

IMPACT Enables more powerful AI applications on personal devices, enhancing privacy and reducing reliance on cloud infrastructure.

RANK_REASON The item describes a new model release with a focus on its practical application and performance on consumer hardware, rather than a frontier model release from a major lab.

Read on dev.to — LLM tag →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

VIDRAFT's POCKET 35B model runs on phones and PCs without GPUs

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: Tool; The item describes a new model release with a focus on its practical application and performance on consumer hardware, rather than a frontier model release from a major lab.
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: model release, product; 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: 95 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 [1]

dev.to — LLM tag TIER_1 English(EN) · AI OpenFree · 2026-07-23 05:17

A 35B model that runs on a GPU-less PC — and on a phone — with stock llama.cpp

<p>There is a quiet, crowded race in AI right now: not in the cloud, but on the device in your hand. On-device models run without a network, keep your data local, and cost nothing per token. Everyone from big tech to the open-source community is pushing that way.</p> <p>One of th…

How we ranked this

COVERAGE [1]

A 35B model that runs on a GPU-less PC — and on a phone — with stock llama.cpp

RELATED ENTITIES

RELATED TOPICS