Unverified50% confidenceBenchmarkExact time
Under a TP4 tensor-parallel configuration, QWEN 3.8 can peak at 100–115 tokens per second.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/11/2026
First Seen
Valid until: 12/10/2026
Sources
Related Entities
Related Claims
UnverifiedQwen 3.8 has a base speed of 22 tokens/s on the M5 Max, which can be boosted to 34 or even 56 tokens/s with MTP enabled.73% similarUnverifiedQwen2.5-Max-0902 has a maximum output of 130,000 tokens, with the limit rising to 260,000 tokens in reasoning mode.69% similarUnverifiedQwen3.7 Max already supports context lengths at the million-token level.68% similarUnverifiedThe Q4_K_M quantization scheme averages approximately 4.8 bits per weight, while the Q8_0 quantization scheme uses 8 bits per weight.66% similarUnverifiedThe Q3_XXS model paired with an F16 KV cache scores approximately 80% on the needle test, while Q3_K_XL paired with a kvarn3 KV cache scores close to 100%.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/896149API
curl https://kongchang.com/api/v1/knowledge/claims/896149MCP
get_claim(id=896149)