Fetching from the wire…
01
02
03
04
05
06
07
08
Tools2026-04-21 · source-backed
Benchmarks on M3 Max show 56.1 vs 52.7 tok/s for Gemma 4 26B. K-quant delivers 4.7x better perplexity than uniform 4-bit. If you're running local agents on Apple Silicon, GGUF is the faster choice right now.
Each link below shares sources, entities, or timing with this story.
Ollama supports Gemma / Shared entities / Shared topic / What happened next
Linked by a graph relationship (Ollama supports Gemma); both cover Gemma, GGUF; overlapping topics (gemma, gguf, running).
Ollama supports Gemma / Shared entity: Gemma / Shared topic / What happened next
Linked by a graph relationship (Ollama supports Gemma); both cover Gemma; overlapping topics (faster, gemma, local, running).
Gemma built by Google / Shared entities / What happened next
Linked by a graph relationship (Gemma built by Google); both cover Gemma, GGUF; picks up the Gemma thread on 2026-08-16.
M5 Max benchmarked against M3 Max / Shared entity: GGUF / Shared topic / What happened next
Linked by a graph relationship (M5 Max benchmarked against M3 Max); both cover GGUF; overlapping topics (agent, local).
Ollama supports Gemma / Shared entity: Gemma / Shared topic / Earlier coverage
Linked by a graph relationship (Ollama supports Gemma); both cover Gemma; overlapping topics (gemma, local).
Gemma built by Google / Shared entity: Gemma / What happened next / Tension
Linked by a graph relationship (Gemma built by Google); both cover Gemma; picks up the Gemma thread on 2026-06-14.
Gemma built by Google / Shared entity: Gemma / What happened next
Linked by a graph relationship (Gemma built by Google); both cover Gemma; picks up the Gemma thread on 2026-06-11.
Ollama supports Gemma / Shared entity: Gemma / Earlier coverage
Linked by a graph relationship (Ollama supports Gemma); both cover Gemma; earlier Gemma coverage from 2026-04-02.