Unverified50% confidenceBenchmarkExact time
ExecuTorch 1B on a simulator requires a 1.14 GB download (6 minutes 12 seconds), approximately 5 seconds to load on each launch, approximately 907 MB of in-app memory during generation, a generation speed of 43 tokens/s, and a median time-to-first-token of 579 ms for subsequent calls.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
UnverifiedIf the quantized model weights are 150 GB, reading the weights once at a bandwidth of 273 GB/s takes approximately 0.55 seconds, giving a theoretical single-token generation speed of approximately 1.8 tokens/s (excluding computation latency and cross-node communication overhead).76% similarUnverifiedV8 Isolates take less than 5 milliseconds to start a new Isolate, consume only 3–5MB of memory, and a single physical server can run hundreds of thousands of Isolates simultaneously.75% similarUnverifiedRunning via llama.cpp on a MacBook Pro with an M4 Pro chip and 24GB unified memory, the text decoding speed is 10.13 tokens/second, with each complete task taking 4 to 7 minutes.72% similarVerifiedFor the 4-bit quantized version of a 7B parameter model, at least 8GB of memory and a modern multi-core CPU are typically required for smooth operation, with inference speeds of approximately 10–30 tokens per second72% similarUnverifiedHarness has approximately 900+ dependencies totaling about 1 GB, and the initial installation typically takes 2 to 5 minutes.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1003198API
curl https://kongchang.com/api/v1/knowledge/claims/1003198MCP
get_claim(id=1003198)