Ouro Hybrid 1.4B — Hardware Requirements & GPU Compatibility
Chat
Ouro Hybrid 1.4B is a 1.5B-parameter open language model from chili-lab. It supports a context window of up to 65,536 tokens. At BF16 it needs about 3.73 GB of VRAM — see which GPUs and Macs can run it below.
152 downloads
8 likesSpecifications
- Publisher
- chili-lab
- Parameters
- 1.5B
- Architecture
- StudentForCausalLM
- Context Length
- 65,536 tokens
- Vocabulary Size
- 49,152
- Release Date
- 2026-05-19
- License
- Other
Get Started
HuggingFace
How Much VRAM Does Ouro Hybrid 1.4B Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 3.7 GB | 16.2 GB | 3.02 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run Ouro Hybrid 1.4B?
BF16 · 3.7 GBOuro Hybrid 1.4B (BF16) requires 3.7 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 5+ GB is recommended. Using the full 66K context window can add up to 12.5 GB, bringing total usage to 16.2 GB. 35 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run Ouro Hybrid 1.4B?
BF16 · 3.7 GB33 devices with unified memory can run Ouro Hybrid 1.4B, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomRelated Models
Frequently Asked Questions
- How much VRAM does Ouro Hybrid 1.4B need?
Ouro Hybrid 1.4B requires 3.7 GB of VRAM at BF16. Full 66K context adds up to 12.5 GB (16.2 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 1.5B × 16 bits ÷ 8 = 3 GB
KV Cache + Overhead ≈ 0.7 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 13.2 GB (at full 66K context)
VRAM usage by quantization
BF163.7 GBBF16 + full context16.2 GB- Can I run Ouro Hybrid 1.4B on a Mac?
Ouro Hybrid 1.4B requires at least 3.7 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 Ouro Hybrid 1.4B locally?
Yes — Ouro Hybrid 1.4B can run locally on consumer hardware. At BF16 quantization it needs 3.7 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Ouro Hybrid 1.4B?
At BF16, Ouro Hybrid 1.4B can reach ~782 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~176 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 ÷ 3.7 × 0.55 = ~782 tok/s
Estimated speed at BF16 (3.7 GB)
~782 tok/s~176 tok/s~584 tok/s~483 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Ouro Hybrid 1.4B?
At BF16, the download is about 3.02 GB.
- Which GPUs can run Ouro Hybrid 1.4B?
35 consumer GPUs can run Ouro Hybrid 1.4B at BF16 (3.7 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 Ouro Hybrid 1.4B?
33 devices with unified memory can run Ouro Hybrid 1.4B at BF16 (3.7 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.