Unverified50% confidenceBenchmarkExact time
In the TP4 configuration on 4 DGX Spark units, measured TTFT is: about 12 seconds for over 60,000 tokens (about 5400 Token/s), about 54 seconds for 260,000 tokens (about 4800 Token/s), and about 4 minutes 54 seconds for 1 million tokens (about 3400 Token/s).
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/20/2026
First Seen
Valid until: 1/18/2027
Sources
4 DGX Sparks Test DeepSeek V4.1 Flash: How Good Is Local Inference Productivity?
bilibiliAI一平米10/20/2026
Related Entities
Related Claims
UnverifiedAt approximately 4K input, TTFT is 23.6 seconds with decoding at 46.6 tok/s; at 8K, 47 seconds and 41.4 tok/s; at 16K, 1 minute 30 seconds and 30.8 tok/s; at 30K, 3 minutes 15 seconds and 31.9 tok/s.77% similarUnverifiedIn simulation experiments, Turbo's streaming TTS was about 3.5 times faster than batch TTS at 20 tokens, and about 14 times faster at 80 tokens.74% similarUnverifiedAn agent task requiring 20 LLM calls with 200 tokens generated each time takes approximately 133 seconds to complete at 30 TPS, but only 13 seconds at 300 TPS.73% 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.73% similarUnverified每条DNS记录都附带TTL值，指定递归解析器可缓存该记录的秒数，常见设置从300秒到86400秒不等72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1077057API
curl https://kongchang.com/api/v1/knowledge/claims/1077057MCP
get_claim(id=1077057)