Unverified50% confidenceBenchmarkExact time
Swift used at most 44K tokens on any single case, while the base version reached a maximum of 203K tokens.
1
Sources
50%
Confidence
Long-term
Relevance
9/25/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe 128K character output limit is approximately equivalent to 30,000–40,000 tokens.65% similarUnverifiedIn tests with the 4-bit quantized version (fitting entirely into 32 GB of VRAM), Ollama reached 240 tokens/s while FreeToken reached 225 tokens/s, making Ollama actually faster.64% similarUnverifiedIf bandwidth reached 2.4 TB/s, the theoretical speed ceiling for a 100 GB model could reach 24 tokens/s, a 60 GB model 40 tokens/s, and a 35 GB model close to 69 tokens/s.63% similarUnverifiedWhen running at 1-bit precision on an M2 Max equipped with 96GB of VRAM, generation speed for simple tasks is consistently around 28–30 tokens/second63% similarUnverifiedCommunity benchmark comparison data: M2 Ultra approximately 20 tokens/second, M3 Ultra 512 GB at 39.8 tokens/second, a single B200 at 119.7 tokens/second, 8× RTX Pro 6000 at approximately 204 tokens/second, a modified RTX 4090 with 48 GB VRAM on a custom backend at 367 tokens/second, and dual H200 at approximately 375 tokens/second.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/951066API
curl https://kongchang.com/api/v1/knowledge/claims/951066MCP
get_claim(id=951066)