Unverified50% confidenceBenchmarkExact time
The model gemma4:e2b-it-qat runs locally via Ollama on a CPU-only i5-1135G7 laptop, with a download size of 4.3 GB, a cold-start time of approximately 14 seconds, a warm-start time of 3.6 to 4.0 seconds, and a speed of approximately 15 to 20 tokens/second.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
UnverifiedThe 4-bit quantized GGUF format version of llama.cpp enables the Llama 3.1 70B model to run on an Apple M2 Ultra with 64GB unified memory at an inference speed of approximately 20–30 tokens/second.70% 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.67% similarVerifiedModern CPU L1 cache access latency is approximately 0.5 nanoseconds, L2 approximately 4 nanoseconds, and a single main memory access requires 60–100 nanoseconds.66% similarUnverifiedThe test hardware was a Raspberry Pi 5 with 8GB of memory, an active heatsink, and dual SSDs; all models were run via llama.cpp and speed was measured using llama-bench.65% similarUnverifiedApple M2/M3 chips adopt a Unified Memory Architecture (UMA), and llama.cpp can achieve approximately 30–50 tokens/second inference speed for 7B models via the Metal API.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1002933API
curl https://kongchang.com/api/v1/knowledge/claims/1002933MCP
get_claim(id=1002933)