Unverified60% confidenceBenchmarkExact time
In the DeepSeek R1 670B (MXFP4 precision) test, Jalapeño achieved approximately 1.7× throughput per watt (19,641 vs. GB300's 11,781), and end-to-end latency was reduced from 5.99 seconds to 1.65 seconds.
2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
9/24/2026
First Seen
Valid until: 12/23/2026
Sources
Related Entities
Related Claims
UnverifiedThrough request-owned speculative KV, in a DeepSeek-V4-Pro 1P1D, MI355X, concurrency-256 scenario, the average TTFT was reduced from 19.4 seconds to 15.1 seconds.70% similarUnverifiedOn GSM8K, OQ4E took 2,450.2 seconds, while 8-bit took as long as 5,471.2 seconds, more than twice the time.66% similarUnverified13B–14B class models (4-bit quantization) see speeds drop to 2–5 tokens per second under this configuration66% similarUnverifiedThe DeepSeek distilled versions range in parameter count from 1.5B to 70B.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/945835API
curl https://kongchang.com/api/v1/knowledge/claims/945835MCP
get_claim(id=945835)