Unverified50% confidenceFactExact time
When using Hybrid Compute for the first time, three local model download options are offered: Gemma (suitable for low-end devices), Qwen 3 (approximately 35B parameters), and Perplexity's own model.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/4/2026
First Seen
Valid until: 1/2/2027
Sources
Related Entities
Related Claims
Unverified可用于本地部署的模型从轻量级的Phi-3、Gemma到重量级的Llama 3、Qwen2.5都可以根据硬件条件自由切换75% similarUnverifiedSeries such as Qwen2.5 and Gemma3 have already released 1B–3B quantized versions optimized specifically for edge scenarios.73% similarUnverifiedNVIDIA has performed local inference optimization for the 27B model in the Qwen3 series on the Jetson platform.70% similarUnverifiedPhi、Gemma、Qwen等系列有小参数版本用于端侧部署和低成本推理场景69% similarPartially VerifiedQwen3.8-Flash-Next adopts a Mixture of Experts (MoE) architecture with 125B total parameters and 6B activated parameters.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/973122API
curl https://kongchang.com/api/v1/knowledge/claims/973122MCP
get_claim(id=973122)