Unverified50% confidenceEventExact time
A developer ran the Qwen3.8-Flash-Next model with a 1 million token context window locally on an Apple M5 Max 128GB device via MLX-serve.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/10/2026
First Seen
Valid until: 12/9/2026
Sources
Related Entities
Related Claims
UnverifiedLocal inference is constrained by the user's hardware: a 7B-parameter quantized model (such as the Q4 version of Llama 3 8B) has a file size of approximately 4–5 GB, can reach 20–40 tokens per second on a Mac with an Apple M-series chip, and may drop to 3–5 tokens per second on a laptop with only an integrated GPU and 8 GB of RAM.73% similarUnverifiedUnder hardware conditions of 16 GB of memory, only models within 5 GB can be accommodated, so the developer used the Qwen 2.5 7B 4-bit quantized model, which is approximately 4.8 GB in size, with an 8K context window.71% similarUnverifiedQwen2.5-Max-0902 supports a context window of 1 million tokens.71% similarUnverifiedThe Fable 5 1M Max model supports a context window of up to 1 million tokens.69% similarUnverified苹果A18 Pro统一内存架构最高支持16GB，内存带宽达68GB/s，Neural Engine算力达35 TOPS68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/888246API
curl https://kongchang.com/api/v1/knowledge/claims/888246MCP
get_claim(id=888246)