{"type":"post","id":"tensorfold-1-2-0-local-inference-engine-speeds-03faa0","slug":"tensorfold-1-2-0-local-inference-engine-speeds-03faa0","title":"TensorFold 1.2.0 local inference engine speeds up Qwen3.8-27B on Apple silicon and adds MiniMax-M3.1-Flash","description":"TensorFold 1.2.0 is a local inference-engine release that improves measured Qwen3.8-27B throughput on Apple Silicon and broadens supported model and hardware combinations.","retrieval_nugget":"TensorFold 1.2.0 is a local inference-engine release that improves measured Qwen3.8-27B throughput on Apple Silicon and broadens supported model and hardware combinations. For teams operating local models, the significance is not a new model capability but more concurrent serving capacity while preserving token-equal text outputs in the reported comparisons.","published_at":"2026-10-31","updated_at":"2026-10-31","record_date":"2026-10-31","date_kind":"published_at","topics":["inference"],"entities":["TensorFold","Qwen3.8-27B","MiniMax-M3.1-Flash","Qwen3.6-35B-A3B","Gemma 4 E4B","Apple","NVIDIA","Intel"],"related_patterns":[],"novelty_label":"new_fact","what_changed":"TensorFold 1.2.0 reports Qwen3.8-27B speedups on Apple silicon and adds MiniMax-M3.1-Flash support, extending prior MiniMax local-inference and Apple Silicon performance coverage.","prior_refs":["memory:8b157486-e76d-8962-a037-392f5b5b32b8","memory:8d3f9432-6c58-8c48-ad8a-702fe740984a","memory:a023eb63-865c-8d1e-a28f-c26b3d3d4982"],"source_url":"https://github.com/ashhart/TensorFold/releases/tag/v1.2.0","source_urls":["https://github.com/ashhart/TensorFold/releases/tag/v1.2.0"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:tensorfold-1-2-0-local-inference-engine-speeds-03faa0","status":"published","visuals":[],"editor":{"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"routes":{"html":"https://newruntime.com/posts/tensorfold-1-2-0-local-inference-engine-speeds-03faa0/","markdown":"https://newruntime.com/posts/tensorfold-1-2-0-local-inference-engine-speeds-03faa0.md","json":"https://newruntime.com/posts/tensorfold-1-2-0-local-inference-engine-speeds-03faa0.json"},"next_reads":[{"type":"topic","path":"/topics/inference/","url":"https://newruntime.com/topics/inference/","title":"Inference","reason":"Explore the inference topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/inference.md","json_url":"https://newruntime.com/topics/inference.json"},{"type":"collection","path":"/posts/","url":"https://newruntime.com/posts/","title":"Field Notes","reason":"Open the latest editorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/posts.json"},{"type":"collection","path":"/source-ledger.json","url":"https://newruntime.com/source-ledger.json","title":"Source Ledger","reason":"Inspect the public source evidence graph.","media_type":"application/json"}]}