Unverified50% confidenceFactExact time
Perplexity currently offers three local orchestration models: Gemma 4 E4B (4-bit quantized, 6.6GB, requires 16GB of memory), Qwen 3.5 35B (requires 32GB of memory) and Perplexity's in-house 19GB model (requires 32GB of memory).
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/24/2026
First Seen
Valid until: 1/22/2027
Sources
Perplexity Hybrid Compute Tested: Privacy Data Never Leaves the Mac
bilibili量子菠萝_10/22/2026
Related Entities
Related Claims
Verified4-bit quantization (such as Q4_K_M) can typically compress the memory footprint of a 3B model from approximately 6GB to approximately 2GB, with a precision loss of less than 2–3%.75% similarVerifiedA 300B INT4 quantized model requires approximately 150–180GB of storage space.75% similarUnverified一张1024×1024的未压缩RGBA纹理占据4MB存储空间74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1092388API
curl https://kongchang.com/api/v1/knowledge/claims/1092388MCP
get_claim(id=1092388)