Tracked topic
Qwen3 is an AI model family developed by Alibaba, released as a set of large language models for natural-language tasks.
…Across Qwen3 0.6B--14B on domain-continual and capability-continual settings, GCWM consistently outperforms data-free baselines, improving retention and final performance without replay data. These results identify geometry conflict as…
["lexar","dram","nand-flash","llms","qwen3"]
…In tests with Llama 3.1 8B and Qwen3-8B, running at ~50% sparsity resulted in near-lossless accuracy across most tasks. Danger zone: Pushing sparsity beyond 60% often leads to sharp…
…After SFT on self-distilled data, the 3B model reaches performance comparable to, and in aggregate slightly above, Qwen3-Omni-30B-A3B-Instruct without using a stronger omni-modal teacher. These results…
Safetensors, llmfan46/Qwen3.5-35B-A3B-uncensored-heretic-v2-Native-MTP-Preserved: https://huggingface.co/llmfan46/Qwen3.5-35B-A3B-uncensored-heretic-v2-Native-MTP-Preserved GGUFs, llmfan46/Qwen3.5-35B-A3B-uncensored-here…
Qwen3.6-35B-A3B speculative decoding is net-negative on RTX 3090
We got 207 tok/s with Qwen3.5-27B on an RTX 3090
https://preview.redd.it/42ak5qmus82h1.png?width=1133&format=png&auto=webp&s=744ea3dfc06c83d0c4d8aa128c39b3238b17d7be Qwen 3.7 Max sitting at 5th, pretty much on par with GPT 5.4 (xhigh) and a notch above the just release…
https://w418ufqpha7gzj-80.proxy.runpod.netStarted for myself, but since Im not using it continuously, sharing it:Open Access Qwen3.6-35B-A3B-UD-Q5_K_M with TurboQuant (TheTom/llama-cpp-turboquant) on RTX 3090 (Runpod spo…
…models from different capability tiers produce harness updates that lead to surprisingly similar gains; even Qwen3.5-9B's updates yield gains comparable to those of Claude Opus~4.6. Second, harness…
["qwen3","lm-studio","llms"]
…Remarkably, RoundPipe enables LoRA fine-tuning of the Qwen3-235B model with 31K sequence length on a single server. RoundPipe is publicly available as an open-source Python library with comprehensive documentation…
…My setup right now is Qwen3.6 35B-A3B running locally on a Lenovo ThinkStation PGX . Hermes sits around it as the agent layer, which means the model can pull from APIs…
…Since the Raspberry Pi 5 is far from ideal for running high-parameter models, I initially went with the Qwen3.5-0.8B model, specifically the one from bartowski’s repo. Once…
["qwen3"]
