Articles tagged "Alibaba"

Open Code Review is Alibaba's open-source AI code review CLI, combining a deterministic pipeline with an LLM agent after two years of internal use. This guide covers installation, configuration, CI integration, and how it compares to CodeRabbit and other tools.

Qwen-Image-2.1, Alibaba's open model (Sep 20, 2026), unifies 7B gen and editing with transparent PNG, 10-image edits. VRAM unofficial; non-commercial license.

Qwen3.8-Omni-Flash: Alibaba's omni-modal model, 1M-token context, $0.15/million input. Weights closed, no local run; text-only output, unlike its predecessor.

Qwen3.8-Flash-Next needs roughly 75GB (1-bit) to 354GB (BF16) of memory depending on quantization. This 125B-total/6B-active open-weight MoE has been run on a single 24GB RTX 4090 via MoE expert offloading, while the official vLLM/SGLang FP8 recipe needs ~250GB across multiple datacenter GPUs. VRAM and GPU tables inside. Updated August 2026.

Qwen3.8-27B weights landed on August 15, 2026. This at-a-glance requirements guide maps VRAM needs to the actual published file sizes: Q4_K_M is 17.1GB and won't fit a 16GB GPU, making IQ4_XS (15.7GB) the practical floor. Licensed Apache-2.0 for commercial use.

Qwen3.8 Max: Alibaba's 2.4T sparse MoE, ~95B active/token. SWE-bench 87.3%. API from $2.00/$6.00/M tokens (in/out). Open weights promised. Updated Aug. 2026.

Qwen3.7 Flash: Alibaba's closed vision model, priced from $0.03 per million input tokens, 1M-token context. Tiered pricing, use cases, limits. Updated Aug. 2026.

Qwen 3.6-27B Dense from Alibaba's Qwen Team, released April 22, 2026: 77.2 on SWE-bench Verified, 59.3 on Terminal-Bench 2.0 (matching Claude 4.5 Opus), 262K-to-1M context, Apache 2.0 license, and 40 tok/s on an RTX 3090 with Q4_K_M — summarized from official sources.

Qwen 3.6 Plus, released April 2, 2026, scores 61.6 on Terminal-Bench 2.0—surpassing Claude Opus 4.6. Explore its 1M token context, 158 tok/s throughput, and 17x cost advantage over Claude Opus in this complete guide.