Small Language Models
8 pieces on Small Language Models.
News & Analysis
Four-Layer Local AI Stack Runs SLMs With No Cloud Dependency
A practical framework for serving, IDE integration, terminal automation, and retrieval — assembling open-weight 1B–14B models into a real development workflow.
IBM Granite 4.2: 30B Model Hits 57.0 on SWE-Bench Verified
IBM's Granite 4.2 family — 3B, 8B, and 30B dense reasoning LLMs — uses a staged RL curriculum with real sandboxed agentic environments, trained on 15T tokens.
GLiNER2.5 Drops Span Enumeration, Opens 4,096-Token Context
Fastino's GLiNER2.5 replaces span enumeration with boundary prediction, removing entity-length limits and reaching 56.17 macro F1 across 16 zero-shot benchmarks.
LFM2.5-DSpark Hits 3.18x GPU Speedup With Zero Output Change
Liquid AI's DSpark draft checkpoints deliver up to 3.18x throughput on H100 and 2.87x on M4 Max MacBook Pro, with bit-identical greedy output.
Needle 2: 45M-Parameter Tool-Calling Model in a 14MB Binary
Cactus Compute's Needle 2 runs a full inference session in 28MB of RAM, hits 500 tokens/sec on a Raspberry Pi 5, and needs no GPU.
Liquid AI LFM2.5-VL-3B: 3.1B On-Device Vision-Language Model
Liquid AI's 3.1B-parameter LFM2.5-VL-3B scores 69.4 across 28 vision benchmarks, matches 4.7B rivals, and adds tool calling for on-device agents.
webAI TwIL-LM: 1.7B and 3B Formal-Logic Models for Local Hardware
webAI releases TwIL-LM, a 1.7B LoRA adapter and 3B merged model for autoformalization, running on 4 GB VRAM under a non-commercial license.
Structured Output with Local LLMs: When Valid JSON Is Not Enough
Gemma 4's 4B model returns schema-valid JSON that still includes the wrong device. Here's the decomposition pattern that fixes it.