Archive
新模型、開放權重、多模態、語音、影像與模型架構。
GitHub Repo
A development-branch reproduction on October 7 suggests Whisper timestamp decoding may mishandle the two-dimensional tensors returned by `generate`, merging batch results or failing at runtime. The report includes a minimal reproduction, but the impact on released versions and any upstream fix remain unconfirmed.
最新模型
Anthropic released Claude Haiku 5.5 on October 7, with adjustable reasoning effort and lower per-token prices for short prompts. AWS is offering the model as well, but long-prompt pricing, cross-region routing, and the cost of real-world tasks still need separate evaluation.
GitHub Repo
A community reproduction on October 6 found that importing a Gemma 4 12B GGUF into Ollama under a name without its size may trigger the wrong prompt template. A proposed fix includes a regression test but has not been merged, and its effect on generation quality remains unmeasured.
最新模型
On October 7, Liquid AI released d1-3B and the experimental d1-omni-600M, which return structured decisions without generating answers token by token. Local and Jetson deployment examples are available, but the low-latency figures depend on warm-up conditions, and evaluation results are still primarily based on the company’s own testing.
最新模型
On October 6, Google released EmbeddingGemma 2, which maps text, code, images, video, and audio into a shared vector space and makes its weights available under Apache 2.0. The model can load encoders as needed, but quantized memory figures and full-precision evaluation results should be interpreted separately.
GitHub Repo
An October 7 Ollama community test found higher latency for long-prompt requests with three decision models using MLX quantized formats on M5 Pro than with BF16. The report includes measurement methods and reproduction instructions, but maintainers have yet to confirm whether dequantization is a bottleneck.
GitHub Repo
A community report dated October 6 says image requests to Qwen3-VL may repeatedly crash the inference process when another large model is already using both GPUs. The report includes a core-dump stack trace, but maintainers have yet to confirm whether memory pressure caused a null-pointer error.
GitHub Repo
A community reproduction posted October 6 suggests ChatOllama may omit the tool-name field used by Ollama when sending tool results. The report includes intercepted requests and prompt-rendering comparisons, but maintainers have not confirmed the issue and no fix has been merged.
最新模型
Mistral launched a public preview of Large 4 on October 6, featuring a native multimodal MoE architecture. Model weights are expected by the end of the month. An independent cybersecurity evaluation found strong vulnerability-handling performance, but passing the test does not mean the original vulnerability was fully fixed.
GitHub Repo
A community report on October 6 says that after Hermes Agent connects to a custom model proxy, cached context length and manual overrides may prevent the proxy from starting. A fix for the ineffective override has been proposed, but remains a draft and does not address cache expiration.
GitHub Repo
A community report on October 6 says Hermes Agent retried an oversized desktop screenshot three times without shrinking it. The report includes error logs and code analysis, but no fix has been merged, and effects on other platforms remain unconfirmed.
GitHub Repo
Community reports from October 5 say that after upgrading Ollama from 0.34.0 to 0.35.1, GLM-OCR’s table output and recognition results may regress. The reporter provided a same-machine version comparison, but the root cause, scope, and fix status remain to be confirmed upstream.