Ouro 2.6B — Hardware Requirements & GPU Compatibility
ChatReasoning
Ouro 2.6B is a 2.7B-parameter open language model from ByteDance. It supports a context window of up to 65,536 tokens. At BF16 it needs about 6.44 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (BF16 · 4K)Best on 24 GB (BF16 · ~102 tok/s · 32K)Macs from 16 GB (BF16 · ~22 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Ouro 2.6B
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve ByteDance/Ouro-2.6B --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 A4000 (16 GB) (3 GB headroom) · BF16
- Generation speed
- ~45 tok/s
- generation speed
- Cost per 1M output tokens
- $0.67
- per 1M output tokens
How Much VRAM Does Ouro 2.6B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 6.4 GB | 18.5 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 32K context · ~102 tok/s |
Selected BF16
Brain floating point 1612.1GBat 16K context
- Weights
- 5.3 GB
- KV cache
- 6.5 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 11.9 GB free · ~102 tok/s
≥50 tok/s needs ≥495 GB/s · RTX 5090 ~181, RTX 3090 Ti ~102
Which Hardware Can Run Ouro 2.6B?
BF16 · 6.4 GBOuro 2.6B (BF16) requires 6.4 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 9+ GB is recommended. Using the full 66K context window can add up to 25.0 GB, bringing total usage to 31.4 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3070 Ti. 151 devices with unified memory can run Ouro 2.6B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), NVIDIA Jetson Orin Nano 8GB (Super).
16–18 GB
16–18 GB tier →fits · 3.9 GB free · up to 16K ctx
18 GPUs · 2 Mac classes · 2 device families
RTX 5080~97Simulate output on RTX 5080RTX 5070 Ti~90Simulate output on RTX 5070 TiRTX 4080 SUPER~74Simulate output on RTX 4080 SUPERM516 GB~17Simulate output on MacBook Air 13" M5 (16 GB)M3 Pro*18 GB~16Simulate output on MacBook Pro 14" M3 Pro (18 GB)iPad~17Simulate output on iPad Pro M5 13" (16 GB)Orin NX~10Simulate output on NVIDIA Jetson Orin NX 16GB20 GB
fits · 7.9 GB free · up to 32K ctx
1 GPU
RX 7900 XT~75Simulate output on RX 7900 XT32–40 GB
fits · 19.9 GB free · up to 64K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~181Simulate output on RTX 5090M5 Max36 GB~50Simulate output on Mac Studio M5 Max (36 GB)M532 GB~17Simulate output on MacBook Air 13" M5 (32 GB)Orin~21Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~14Simulate 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 |
|---|---|---|---|---|
| MiniCPM5 2BOpenBMB | — | 2.5 GB | ~345 | same size |
| North Micro Vision InstructCohere | — | 7.1 GB | ~119 | same size |
| LFM2.5 2.6BLiquid AI | — | 2.3 GB | ~321 | same size |
| Granite 3.1 2B InstructIBM | — | 3.2 GB | ~329 | same size |
| Gemma 2 2B ITGoogle | — | 2.5 GB | ~379 | same size |
| Phi 2Microsoft | — | 2.6 GB | ~248 | same size |
Specifications
- Publisher
- ByteDance
- Parameters
- 2.7B
- 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 2.6B need?
Ouro 2.6B requires 6.4 GB of VRAM at BF16. Full 66K context adds up to 25.0 GB (31.4 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 2.7B × 16 bits ÷ 8 = 5.3 GB
KV Cache + Overhead ≈ 1.1 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 ≈ 26.1 GB (at full 66K context)
VRAM usage by quantization
Can I run Ouro 2.6B on a Mac?
Yes — Mac Mini M2 Pro (16 GB) and 133 other Macs can run Ouro 2.6B. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 6.4 GB of usable unified memory (RAM minus macOS overhead).
Can I run Ouro 2.6B locally?
Yes — Ouro 2.6B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Ouro 2.6B?
At BF16, Ouro 2.6B can reach ~745 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~102 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 ÷ 6.4400 × 0.65 = ~807 tok/s
Estimated speed at BF16 (6.4 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Ouro 2.6B?
At BF16, the download is about 5.34 GB.
Which GPUs can run Ouro 2.6B?
52 consumer GPUs can run Ouro 2.6B at BF16. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT, AMD Radeon RX 7600. 40 GPUs have plenty of headroom for comfortable inference.
Which devices can run Ouro 2.6B?
151 devices with unified memory can run Ouro 2.6B at BF16 (6.4 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.