Ouro 1.4B Thinking — Hardware Requirements & GPU Compatibility
ChatReasoning
Ouro 1.4B Thinking is a 1.4B-parameter open language model from ByteDance. It supports a context window of up to 65,536 tokens. At BF16 it needs about 3.57 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 · ~184 tok/s · 64K)Macs from 8 GB (BF16 · ~20 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Ouro 1.4B Thinking
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve ByteDance/Ouro-1.4B-Thinking --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
- ~66 tok/s
- generation speed
- Cost per 1M output tokens
- $0.30
- per 1M output tokens
How Much VRAM Does Ouro 1.4B Thinking Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 3.6 GB | 9.6 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 64K context · ~184 tok/s |
Selected BF16
Brain floating point 166.4GBat 16K context
- Weights
- 2.9 GB
- KV cache
- 3.2 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 17.6 GB free · ~184 tok/s
≥50 tok/s needs ≥274 GB/s · RTX 5090 ~326, RTX 3090 Ti ~184
Which Hardware Can Run Ouro 1.4B Thinking?
BF16 · 3.6 GBOuro 1.4B Thinking (BF16) requires 3.6 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 16.1 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run Ouro 1.4B Thinking, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), MacBook Air 13" M3 (8 GB).
≤ 11 GB
≤ 11 GB tier →fits · 1.6 GB free · up to 16K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~138Simulate output on RTX 3080RTX 2080 Ti~112Simulate output on RTX 2080 TiRTX 3070 Ti~111Simulate output on RTX 3070 TiM3*8 GB~20Simulate output on iMac 24" M3 (8 GB)Orin Nano~19Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~13Simulate output on iPhone 1720 GB
fits · 13.6 GB free · up to 64K ctx
1 GPU
RX 7900 XT~135Simulate output on RX 7900 XT32–40 GB
fits · 25.6 GB free · up to 64K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~326Simulate output on RTX 5090M5 Max36 GB~90Simulate output on Mac Studio M5 Max (36 GB)M532 GB~30Simulate output on MacBook Air 13" M5 (32 GB)Orin~37Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~25Simulate 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 |
|---|---|---|---|---|
| Inkling Small DSpark PreviewRadixArk | — | 1.5 GB | ~555 | 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 |
| Granite 3.0 1B A400m InstructIBM | — | 1.3 GB | ~524 | same size |
| Qwen2.5 1.5B InstructAlibaba | — | 1.7 GB | ~512 | same size |
Specifications
- Publisher
- ByteDance
- Parameters
- 1.4B
- Architecture
- OuroForCausalLM
- Context Length
- 65,536 tokens
- Vocabulary Size
- 49,152
- Release Date
- 2025-10-28
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Ouro 1.4B Thinking need?
Ouro 1.4B Thinking requires 3.6 GB of VRAM at BF16. Full 66K context adds up to 12.5 GB (16.1 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 1.4B × 16 bits ÷ 8 = 2.9 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 1.4B Thinking on a Mac?
Yes — Mac Mini M2 (8 GB) and 145 other Macs can run Ouro 1.4B Thinking. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 3.6 GB of usable unified memory (RAM minus macOS overhead).
Can I run Ouro 1.4B Thinking locally?
Yes — Ouro 1.4B Thinking can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Ouro 1.4B Thinking?
At BF16, Ouro 1.4B Thinking can reach ~1345 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~184 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 ÷ 3.57 × 0.65 = ~1457 tok/s
Estimated speed at BF16 (3.6 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Ouro 1.4B Thinking?
At BF16, the download is about 2.87 GB.
Which GPUs can run Ouro 1.4B Thinking?
52 consumer GPUs can run Ouro 1.4B Thinking 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 1.4B Thinking?
163 devices with unified memory can run Ouro 1.4B Thinking at BF16 (3.6 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.