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.
Runs great on a 24 GB GPU
Runs from 8 GB (BF16 · 16K)Best on 24 GB (BF16 · ~176 tok/s · 64K)Macs from 8 GB (BF16 · ~19 tok/s)
Other
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Ouro Hybrid 1.4B
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve chili-lab/Ouro-hybrid-1.4B --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Other ways
each opens step-by-stepRun in cloud
Fits on RTX 3060 12GB (5 GB headroom) · BF16
- Generation speed
- ~63 tok/s
- generation speed
- Cost per 1M output tokens
- $0.37
- per 1M output tokens
How Much VRAM Does Ouro Hybrid 1.4B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 3.7 GB | 9.8 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 64K context · ~176 tok/s |
Selected BF16
Brain floating point 166.6GBat 16K context
- Weights
- 3.0 GB
- KV cache
- 3.2 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 17.5 GB free · ~176 tok/s
≥50 tok/s needs ≥287 GB/s · RTX 5090 ~312, RTX 3090 Ti ~176
Which Hardware 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. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run Ouro Hybrid 1.4B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), MacBook Air 13" M3 (8 GB).
≤ 11 GB
≤ 11 GB tier →fits · 1.4 GB free · up to 16K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~133Simulate output on RTX 3080RTX 2080 Ti~107Simulate output on RTX 2080 TiRTX 3070 Ti~106Simulate output on RTX 3070 TiM3*8 GB~19Simulate output on iMac 24" M3 (8 GB)Orin Nano~18Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~13Simulate output on iPhone 1720 GB
fits · 13.4 GB free · up to 64K ctx
1 GPU
RX 7900 XT~129Simulate output on RX 7900 XT32–40 GB
fits · 25.4 GB free · up to 64K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~312Simulate output on RTX 5090M5 Max36 GB~86Simulate output on Mac Studio M5 Max (36 GB)M532 GB~29Simulate output on MacBook Air 13" M5 (32 GB)Orin~36Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~24Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at BF16
Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| MiniCPM V 4.7 1BOpenBMB | — | 1.6 GB | ~512 | same size |
| Granite 4.0 1BIBM | — | 2.6 GB | ~452 | same size |
| LFM2 VL 1.6BLiquid AI | — | 1.5 GB | ~496 | same size |
| Qwen Base Invoicev1.01 1.5BLaaP-ai | — | 1.7 GB | ~512 | same size |
| OLMo 2 0425 1B InstructAllen AI | — | 1.7 GB | ~449 | same size |
| OpenMath Nemotron 1.5BNVIDIA | — | 1.7 GB | ~512 | same size |
Specifications
- Publisher
- chili-lab
- Parameters
- 1.5B
- Architecture
- StudentForCausalLM
- Context Length
- 65,536 tokens
- Vocabulary Size
- 49,152
- Release Date
- 2026-05-19
- License
- Other
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)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 13.2 GB (at full 66K context)
VRAM usage by quantization
Can I run Ouro Hybrid 1.4B on a Mac?
Yes — Mac Mini M2 (8 GB) and 145 other Macs can run Ouro Hybrid 1.4B. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 3.7 GB of usable unified memory (RAM minus macOS overhead).
Can I run Ouro Hybrid 1.4B locally?
Yes — Ouro Hybrid 1.4B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Ouro Hybrid 1.4B?
At BF16, Ouro Hybrid 1.4B can reach ~1287 tok/s on AMD Instinct MI350X. 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: NVIDIA B200 → 8000 ÷ 3.73 × 0.65 = ~1394 tok/s
Estimated speed at BF16 (3.7 GB)
Real-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?
52 consumer GPUs can run Ouro Hybrid 1.4B at BF16. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 52 GPUs have plenty of headroom for comfortable inference.
Which devices can run Ouro Hybrid 1.4B?
163 devices with unified memory can run Ouro Hybrid 1.4B at BF16 (3.7 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.