Unverified50% confidenceReleaseExact time
On October 15, 2025, Black Forest Labs released the open-weights Flux 3 Image Klein, with 5.6B parameters, which can run on an NVIDIA GPU with 8GB of VRAM after INT8 quantization.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/21/2026
First Seen
Valid until: 1/19/2027
Sources
Related Entities
Related Claims
UnverifiedOpen-source models such as LLaMA 3, Mistral, and Qwen 2.5 can already run smoothly on mainstream consumer-grade GPUs (such as the RTX 4090) at parameter scales ranging from 7B to 14B.57% similarUnverifiedAlibaba's Tongyi Qianwen officially released the Qwen3.8-Flash-Next (Qianwen 308 Flash NEX) model, with a total parameter count of 181.5B.56% similarUnverifiedUnsloth released version v0.1.909-beta, adding local running and fine-tuning support for DeepSeek-V4.1-Flash-1017 and FLUX.3 Image Klein.55% similarUnverifiedvLLM provides day-0 support for NVIDIA Vera Rubin NVL72, reporting 7.8x throughput per GPU versus GB200 NVL72 (AgentX) and 3.7x VLM throughput versus GB300 (MLPerf v6.1), with locality domains tuned for MoE routing.55% similarUnverified盘古2.0 Flash在GPQA Diamond科学推理测试中（Thinking模式）得分83.7，低于千问3.6 35B的86、27B稠密模型的87.8和DeepSeek V4 Flash的88.155% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1082214API
curl https://kongchang.com/api/v1/knowledge/claims/1082214MCP
get_claim(id=1082214)