VibeThinker 1.5B — Hardware Requirements & GPU Compatibility
ChatMathCode
VibeThinker 1.5B is a 1.8B-parameter open language model from WeiboAI. It supports a context window of up to 131,072 tokens. At BF16 it needs about 3.91 GB of VRAM — see which GPUs and Macs can run it below.
968 downloads
524 likesSpecifications
- Publisher
- WeiboAI
- Parameters
- 1.8B
- Architecture
- Qwen2ForCausalLM
- Context Length
- 131,072 tokens
- Vocabulary Size
- 151,936
- Release Date
- 2025-11-24
- License
- MIT
Get Started
HuggingFace
How Much VRAM Does VibeThinker 1.5B Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 3.9 GB | 7.6 GB | 3.55 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run VibeThinker 1.5B?
BF16 · 3.9 GBVibeThinker 1.5B (BF16) requires 3.9 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 6+ GB is recommended. Using the full 131K context window can add up to 3.7 GB, bringing total usage to 7.6 GB. 35 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run VibeThinker 1.5B?
BF16 · 3.9 GB33 devices with unified memory can run VibeThinker 1.5B, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomRelated Models
Frequently Asked Questions
- How much VRAM does VibeThinker 1.5B need?
VibeThinker 1.5B requires 3.9 GB of VRAM at BF16. Full 131K context adds up to 3.7 GB (7.6 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 1.8B × 16 bits ÷ 8 = 3.6 GB
KV Cache + Overhead ≈ 0.3 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 4 GB (at full 131K context)
VRAM usage by quantization
BF163.9 GBBF16 + full context7.6 GB- Can I run VibeThinker 1.5B on a Mac?
VibeThinker 1.5B requires at least 3.9 GB at BF16, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run VibeThinker 1.5B locally?
Yes — VibeThinker 1.5B can run locally on consumer hardware. At BF16 quantization it needs 3.9 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is VibeThinker 1.5B?
At BF16, VibeThinker 1.5B can reach ~746 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~168 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: AMD Instinct MI300X → 5300 ÷ 3.9 × 0.55 = ~746 tok/s
Estimated speed at BF16 (3.9 GB)
~746 tok/s~168 tok/s~557 tok/s~461 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of VibeThinker 1.5B?
At BF16, the download is about 3.55 GB.
- Which GPUs can run VibeThinker 1.5B?
35 consumer GPUs can run VibeThinker 1.5B at BF16 (3.9 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 35 GPUs have plenty of headroom for comfortable inference.
- Which devices can run VibeThinker 1.5B?
33 devices with unified memory can run VibeThinker 1.5B at BF16 (3.9 GB), including Mac Mini M4 (16 GB), Mac Mini M4 (32 GB), Mac Mini M4 Pro (24 GB), Mac Mini M4 Pro (48 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.