VibeThinker — local AI model by WeiboAI
Written by Jakub Rusinowski · Last updated
MIT-licensed reasoning fine-tunes that argue the case for small models: VibeThinker-3B scores 94.3 on AIME26, matching what DeepSeek V3.2 reaches at 671B. Trained with the Spectrum-to-Signal pipeline — explore solution diversity during SFT, then reinforce the correct signal with RL. Vendor-reported and contested; treat the headline comparison as a claim about a narrow benchmark family, not general capability.
Variants
The smallest VibeThinker variant needs about 2 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache.
| Model | VRAM at Q4 | VRAM | Context | Run it |
|---|---|---|---|---|
| VibeThinker 3B → 3B | ~2.7 GB | 131,072 | ollama run vibethinker | |
| VibeThinker 1.5B → 1.5B | ~1.7 GB | 131,072 | ollama run vibethinker |
Memory is quantized weights plus overhead at Q4_K_M, from the same engine as the GPU & VRAM checker.
How to run VibeThinker locally
Install Ollama, then pull the tag.
ollama run vibethinkerPick a size above for its own VRAM figure, speed estimate and install command.
Licence
Commercial use permitted. No usage restrictions beyond attribution.
Applies to: VibeThinker 3B, VibeThinker 1.5BRecommended GPU
The cheapest catalogued GPU that runs VibeThinker locally (min 2 GB VRAM) is the Intel Arc B570 (10 GB).
Can I run VibeThinker on my GPU?
VibeThinker — frequently asked questions
How much VRAM does VibeThinker need?
VibeThinker needs about 2 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: VibeThinker 3B (3 GB, Q4_K_M); VibeThinker 1.5B (2 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run VibeThinker on an RTX 4090 (24 GB)?
Yes — VibeThinker runs on an RTX 4090 (24 GB) and other 24 GB cards such as the RTX 3090. Smaller variants also fit comfortably on 8–16 GB GPUs at Q4_K_M.
What quantization should I use for VibeThinker?
Q4_K_M is the best balance of quality and VRAM for VibeThinker in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.
How do I run VibeThinker with Ollama?
VibeThinker has no local Ollama tag — the published tag is cloud-hosted, so running it sends your prompts to a hosted GPU rather than your own machine.