Apple M5 Max
PulseAugur coverage of Apple M5 Max — every cluster mentioning Apple M5 Max across labs, papers, and developer communities, ranked by signal.
4 day(s) with sentiment data
-
Recursive Superintelligence releases Flint, a 40B MoE coding model
Recursive Superintelligence has launched Flint, a 40B parameter Mixture-of-Experts (MoE) model designed for coding agents. This model, which uses 2.5B active parameters per token, was developed with the assistance of Re…
-
Liquid AI's LFM2.5-24B-A2B model offers fast inference but high RAM needs
Liquid AI has released its LFM2.5-24B-A2B model, a 24 billion parameter mixture-of-experts model that only utilizes 2.45 billion parameters per token. This architecture allows for faster decoding speeds, with Liquid rep…
-
Liquid AI releases LFM2.5-24B-A2B for fast on-device agents
Liquid AI has released LFM2.5-24B-A2B, a 24 billion parameter Mixture-of-Experts (MoE) model designed for on-device agents. This model activates approximately 2 billion parameters per token and is optimized for multi-st…
-
LiquidAI releases LFM2.5-24B-A2B for efficient on-device AI agents
LiquidAI has released LFM2.5-24B-A2B, a new reasoning-focused language model designed for efficient on-device agent deployment. Despite having fewer parameters than competitors like Qwen3.6-35B-A3B, it demonstrates comp…
-
Bonsai quantization shrinks LLMs to 5.9GB with 98.2% intelligence retained
A new method for quantizing large language models, dubbed "Bonsai," has been developed, significantly reducing model size while retaining a high percentage of intelligence. This technique compresses 27B-class models to …
-
Swift-1.5-Qwen3.8-27b-oQ8e-mtp benchmarks on Apple M5 Max
A user benchmarked the Swift-1.5-Qwen3.8-27b-oQ8e-mtp model on an Apple M5 Max chip, achieving a generation speed of 34.6 tokens/second. The Swift model produced significantly fewer tokens on average across various scen…
-
Local VLM pipeline Scribe benchmarked for clinical form data extraction
A new local pipeline called Scribe has been benchmarked for its ability to convert handwritten clinical forms into structured data. The pipeline, designed for offline-first health settings, was tested across nine config…
-
Qwen3.8-27B performance tested on Apple M5 Max
A user benchmarked the Qwen3.8-27B model on an Apple M5 Max chip, comparing its performance with "thinking on xhigh" versus "thinking off." The "thinking on xhigh" setting resulted in 5.5 times more tokens processed and…
-
Liquid AI unveils compact LFM2.5-VL-3B vision model for local processing
Liquid AI has released a compact vision model, LFM2.5-VL-3B, featuring 3.1 billion parameters. This model achieves a processing speed of 228 tokens per second on Apple M5 Max processors. The development signifies a brea…
-
Liquid AI releases 3B vision-language model for on-device use
Liquid AI has launched LFM2.5-VL-3B, a 3.1 billion parameter vision-language model designed for on-device applications. This model excels at reading digital screens, identifying objects with coordinates, and processing …
-
Laptop CPU performance varies significantly on battery power, tests reveal
A recent comparison of laptop performance on battery versus AC power revealed significant differences across major CPU manufacturers. While Intel and Apple demonstrated the most consistent performance, with minimal drop…
-
PrismML releases Bonsai 27B, a 27B LLM for offline mobile use
PrismML has released Bonsai 27B, a 27-billion-parameter large language model capable of running offline on mobile devices like the iPhone 17 Pro Max. The model achieves its small footprint through a novel 1-bit training…
-
Study explores ontology-amplified distillation for sovereign enterprise LLMs
A new study explores methods for adapting sovereign enterprise language models, focusing on ontology-amplified distillation and contextuality auditing. Researchers fine-tuned a Qwen3.6-27B model using an ontology and pr…
-
MacBook Pro M5 Max vs M4 Max for Local LLMs: User Seeks Advice
A data scientist is seeking advice on whether to purchase a refurbished MacBook Pro with an M4 Max chip or a new MacBook Pro with an M5 Max chip for running local large language models. The M5 Max offers a slight increa…