Unverified50% confidenceBenchmarkExact time
In a case test, Gemma took approximately 13.78 seconds to analyze a three-page PDF financial report, generating 1,064 tokens at a speed of 16 tokens per second.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/17/2026
First Seen
Valid until: 12/16/2026
Sources
Related Entities
Related Claims
UnverifiedIn this test, the prefill speed was fixed at approximately 500–600 tokens/s, and the time to first token increased linearly with input length.72% similarUnverifiedIn the long-context archiving experiment, 8 requests each input approximately 261,000+ tokens and each completed approximately 1,022 outputs; the total throughput of the joint decoding window was 214.85 tokens per second, approximately 26.86 per request, but the window was only approximately 2.28 seconds and prefilling was serial or interleaved.71% similarUnverifiedOn an 8GB GPU, the token generation speed is approximately 4.2 to 5 tokens/second, and decreases from around 6 tokens/second to approximately 4.2 as the context grows longer.68% similarUnverifiedSome users found in tests with 3 coding prompts that completion times were consistently in the 30–45 second range, with 3.8 Flash being at most about 5 seconds faster.68% similarVerifiedIn decode speed tests, speeds of approximately 45 tokens/second are achievable within 20,000 tokens, dropping sharply to approximately 20 tokens/second beyond 30,000 tokens.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/930309API
curl https://kongchang.com/api/v1/knowledge/claims/930309MCP
get_claim(id=930309)