AI-ML
Ollama v0.17.5
RESUMEN
New models - Qwen3.5: the small Qwen 3.5 model series is now available in 0.8B, 2B, 4B and 9B parameter sizes. What's Changed Fixed crash in Qwen 3.5 models when split over GPU & CPU Fixed issue where Qwen 3.5 models would repeat themselves due t
Descripción Detallada
New models - Qwen3.5: the small Qwen 3.5 model series is now available in 0.8B, 2B, 4B and 9B parameter sizes. What's Changed Fixed crash in Qwen 3.5 models when split over GPU & CPU Fixed issue where Qwen 3.5 models would repeat themselves due to no presence penalty (note: you may have to redownload the `qwen3.5` models: `ollama pull qwen3.5:35b` for example) `ollama run --verbose` will now show peak memory usage when using Ollama's MLX engine Fixed memory issues and crashes in MLX runner * Fixed issue where Ollama would not be able to run models imported from Qwen3.5 GGUF files Full Changelog:
Se añaden nuevos modelos Qwen 3.5 y se corrigen varios errores.
- Nuevos modelos Qwen 3.5 disponibles en tamaños de 0.8B, 2B, 4B y 9B.
- Se solucionó un fallo al usar modelos Qwen 3.5 en GPU y CPU.
- Se arregló un problema de repetición en modelos Qwen 3.5 por falta de penalización de presencia.
- Ahora `ollama run --verbose` muestra el uso máximo de memoria en el motor MLX.
A quién le importa
Todos los que usen modelos Qwen 3.5.
Generado por IA · puede contener errores
Releases Relacionados
AI-ML
Ollama v0.32.5
## What's Changed * Fixed an MLX Metal bug that could reduce output quality for NVFP4 models, particularly Laguna. **Full Changelog**: https://github.com/ollama/ollama/compare/v0.32.4...v0.32.5
AI-ML
Ollama v0.32.4
## What's Changed - Support Laguna on Apple GPUs via the MLX engine - Quantize draft-model output heads at the requested type when creating speculative-decoding drafts. - Fixed Qwen3 MoE decoding for differently-quantized experts, plus faster packed gate/up projection (~4–9% on M5 Max). **Full
AI-ML