VibeThinker 1.5B — VRAM, speed & local setup
Written by Jakub Rusinowski · Last updated
The original VibeThinker, fine-tuned from Qwen2.5-Math-1.5B. Reports 80.3 / 74.4 / 50.4 on AIME24, AIME25 and HMMT25 — above DeepSeek R1 on those three at roughly 1/400th the parameter count. Under 2 GB at Q4_K_M, so it runs on a phone.
VibeThinker 1.5B needs about 2 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.
VRAM and speed by quantization
Quoted against NVIDIA RTX 4090 (24 GB). Weights plus overhead only: this model's architecture is unpublished, so no KV cache is added.
| Quant | Memory | VRAM | Speed (est.) | Fit |
|---|---|---|---|---|
| Q2_K 2.63 bpw | 1.3 GB | ~298 tok/s | Fits | |
| Q3_K_M 3.41 bpw | 1.5 GB | ~281 tok/s | Fits | |
| Q4_K_M 4.83 bpw | 1.7 GB | ~255 tok/s | Fits | |
| Q5_K_M 5.67 bpw | 1.9 GB | ~242 tok/s | Fits | |
| Q6_K 6.56 bpw | 2.1 GB | ~229 tok/s | Fits | |
| Q8_0 8.50 bpw | 2.4 GB | ~206 tok/s | Fits | |
| F16 16.00 bpw | 3.9 GB | ~148 tok/s | Fits |
Black marker = usable memory on the NVIDIA RTX 4090 (24 GB). Estimates from the memory-bandwidth roofline on the methodology page. VibeThinker 1.5B VRAM calculator →
Get VibeThinker 1.5B running
The cheapest catalogued GPU that runs VibeThinker 1.5B is the Intel Arc B570 (10 GB).
or compare on Vast.ai from $0.35/hr (typical low · varies)
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
How to run VibeThinker 1.5B
Install Ollama, then run:
ollama run vibethinkerSpecifications
Verified — Checked against the primary source — the model card or the vendor spec page — and corroborated by a second independent source.
- Parameters
- 1.54 Billion
- Context window
- 131,072
- Architecture
- Dense Transformer (Qwen2.5-Math-1.5B base)
- Provider
- WeiboAI
- Licence
- MIT
- Practical deployment
- Edge device (phone, SBC)
- Specified at
- Q4_K_M
- System RAM
- 4 GB
- Record updated
- 2026-09-06
Commercial use permitted. No usage restrictions beyond attribution.
Quality and use cases
Scores as published by the model’s authors or an independent evaluator — quality, not throughput, and not measured by us.
| Benchmark | Score | Provenance |
|---|---|---|
| AIME 2024 | 80.3 / 100 % | vendor-claimed · https://github.com/WeiboAI/VibeThinker |
| AIME 2025 | 74.4 / 100 % | vendor-claimed · https://github.com/WeiboAI/VibeThinker |
Can I run VibeThinker 1.5B on my GPU?
Other VibeThinker sizes
VibeThinker 1.5B — frequently asked questions
How much VRAM does VibeThinker 1.5B need?
About 2 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.
Does VibeThinker 1.5B run on an RTX 4090 (24 GB)?
Yes. VibeThinker 1.5B needs about 2 GB at Q4_K_M, inside a 24 GB card, at an estimated 255 tokens/sec.
How do I run VibeThinker 1.5B locally?
Install Ollama and run `ollama run vibethinker`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.
What other sizes does VibeThinker come in?
VibeThinker 3B (3 GB), VibeThinker 1.5B (2 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.