Unverified50% confidenceReleaseExact time
Ollama 0.19 was released on March 30 and switched to the MLX backend on Apple Silicon, with decoding speed jumping from 58 tokens/s to 112.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/13/2026
First Seen
Valid until: 1/11/2027
Sources
Related Entities
Related Claims
UnverifiedAccording to Stridenote, Ollama tests showed that Qwen3.5 35b's speed jumped from 58 token/s to 112 token/s after switching to Apple Silicon's MLX.75% similarUnverifiedIn short-answer scenarios, on the same M4 Mac, merely changing the power mode jumps the speed from 28.5 tokens/s to 109.6 tokens/s, a difference of 3.84 times.63% similarUnverifiedMTP speculative decoding raised tokens per second from 50.2 to 95 on the Apple Silicon coding benchmark, nearly doubling the throughput.62% 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.61% similarUnverifiedOn an RTX Pro 6000 (96 GB VRAM), the official FP8 version combined with built-in MTP speculative decoding can reach approximately 120 tokens/second, with quality nearly indistinguishable from 16-bit.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1015144API
curl https://kongchang.com/api/v1/knowledge/claims/1015144MCP
get_claim(id=1015144)