What are you looking for?

Measuring PCIe transfer under dual GPU with pipeline & tensor llama.cpp

AI·A user shares benchmarks of dual RTX 3090 and Titan RTX cards running llama.cpp with Qwen3.6-27B at 180k context, comparing tensor and pipeline parallel modes for PCIe transfer efficiency.

I benched quad 5060Tis for code generation with Qwen3.6-27B so you don't have to (it's really good)

AI·The author benches a quad 5060Ti setup for Qwen3.6-27B code generation using MTP, reporting 608 tokens/s prefill and 52.2 tokens/s decode at 256k context on a cost-effective build.

next best jump from qwen 3.6 27b

AI·Community discusses upgrades from Qwen3.6-27B, recommending options like DeepSeek V4 Flash or GLM-5.2 requiring 100-250GB VRAM for noticeable performance gains.

When the Judge Changes, So Does the Measurement: Auditing LLM-as-Judge Reliability

AI·LLM-as-judge scores fluctuate across evaluators even with fixed candidate responses, treating the issue as measurement validity. Across four datasets, scaling Qwen3 from 1.7B to 32B parameters yields only limited adjacent gains, while MiniMax M2-to-M2.7 API upgrades show none; stronger judges reduce but do not eliminate position and verbosity biases, with repeated juries offering little benefit under correlated errors.

I feel like I'm not using my hardware efficiently

AI·User with RTX 4090, 3090Ti, and 128GB RAM struggles to run larger models like 122B due to VRAM limits while Qwen3.6-27B runs efficiently without using system RAM.

Running Qwen3 30B A3B at 50 tok/s on RTX 5060 Ti

AI·Achieves 50-54 tok/s for Qwen3 30B A3B float8 on 16GB RTX 5060 Ti using custom CUDA/C++.

Dual 3060 MoE loading issue.

AI·Identifies dual 3060 MoE loading limit at 12 layers VRAM for Qwen3 35B/122B with CPU offload.

Diarization-Guided Qwen-ASR Adaptation for Multilingual Two-Speaker Conversational Speech

AI·Researchers developed SQZ-Qwen-ASR-1.7B for MLC-SLM 2026 Task 1, combining a modular speaker diarization front-end (VAD, CAMPPlus embeddings, spectral clustering, RTTM segmentation) with Qwen3-ASR-1.7B adapted via full supervised fine-tuning, LoRA on TTS-generated synthetic speech, and GRPO reinforcement learning for lower tcpMER (23.70 on dev set, 17.97 on eval set).

Is it possible to run Qwen 122B in 64GB ram + 24gb vram ? If so, how ?

AI·Discusses feasibility of running Qwen 122B on 64GB RAM + 24GB VRAM and suitable settings.

CTX: How far can you reasonably go with Qwen 3.6 27B?

AI·Asks how far context window can be stretched with Qwen 3.6 27B at Q8_0 before reliability drops.

Why are MoE models so belittled?

AI·Questions why providers make high-parameter MoE models (e.g. 122B with 10B active) instead of simpler dense equivalents.

Qwen3.6 35B-A3B (Q8_0, no KV quant) single prompt in opencode: "Create a beautiful, relaxing flight simulator in a single html file with mountains, clouds, and endless procedural terrain"

AI·Qwen3.6 35B-A3B Q8_0 model (no KV quant) generates full HTML flight simulator in single prompt and is praised as stronger than Q4_K_M on GPU due to better CPU performance.