Opt 1.3B — Hardware Requirements & GPU Compatibility
Chat
Opt 1.3B is a 1.3B-parameter open language model from Meta. It supports a context window of up to 2,048 tokens. At FP16 it needs about 2.86 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (FP16 · 2K)Best on 24 GB (FP16 · ~229 tok/s · 2K)Macs from 8 GB (FP16 · ~25 tok/s)
Other
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Opt 1.3B
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
vllm serve facebook/opt-1.3b --max-model-len 2048vLLM repo with its own quantisation
Download: Weights on Hugging Face
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on RTX 3080 Ti (12 GB) (9 GB headroom) · FP16
- Generation speed
- ~207 tok/s
- generation speed
- Cost per 1M output tokens
- $0.16
- per 1M output tokens
How Much VRAM Does Opt 1.3B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 2.9 GB | — | 16-bit · full — Full half-precision — baseline for inference | Fits: 2K context · ~229 tok/s |
Selected FP16
Full half-precision2.9GBat 2K context
- Weights
- 2.3 GB
- KV cache
- 0.2 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 21.1 GB free · ~229 tok/s
≥50 tok/s needs ≥220 GB/s · RTX 5090 ~407, RTX 3090 Ti ~229
Which Hardware Can Run Opt 1.3B?
FP16 · 2.9 GBOpt 1.3B (FP16) requires 2.9 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 4+ GB is recommended. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run Opt 1.3B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 5.1 GB free · up to 2K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~173Simulate output on RTX 3080RTX 2080 Ti~140Simulate output on RTX 2080 TiRTX 3070 Ti~138Simulate output on RTX 3070 TiM3*8 GB~25Simulate output on iMac 24" M3 (8 GB)Orin Nano~23Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~17Simulate output on iPhone 1720 GB
fits · 17.1 GB free · up to 2K ctx
1 GPU
RX 7900 XT~168Simulate output on RX 7900 XT32–40 GB
fits · 29.1 GB free · up to 2K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~407Simulate output on RTX 5090M5 Max36 GB~113Simulate output on Mac Studio M5 Max (36 GB)M532 GB~38Simulate output on MacBook Air 13" M5 (32 GB)Orin~47Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~31Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at FP16
How good is Opt 1.3B?
llmrun Score blends public benchmark boards into one number; 100 = the average open model.
Not enough data yet for an llmrun Score.
A Score needs results on enough independent boards. How the Composite Score is built
Benchmarks
The 6 boards that weigh most in the llmrun Score, of 7 with a result for this model; badges show who ran the test.
- MMLU
Epoch AI · May 2022Lab-reported
Lab-reported25.1%
#85/85 open
- HellaSwag
Epoch AI · May 2022Lab-reported
Lab-reported69.9%
#36/47 open
- ARC Challenge
Epoch AI · May 2022Lab-reported
Lab-reported35.8%
#48/56 open
- WinoGrande
Epoch AI · May 2022Lab-reported
Lab-reported64.7%
#36/51 open
- BoolQ
Epoch AI · May 2022Lab-reported
Lab-reported65.0%
#31/38 open
- OpenBookQA
Epoch AI · May 2022Lab-reported
Lab-reported39.8%
#18/26 open
Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| MiniCPM V 4.6 ThinkingOpenBMB | — | 1.5 GB | ~580 | same size |
| Inkling Small DSpark PreviewRadixArk | — | 1.5 GB | ~555 | same size |
| T5gemma L L Ul2 ITGoogle | — | 4.3 GB | ~240 | same size |
| Granite 3.0 1B A400m InstructIBM | — | 1.3 GB | ~524 | same size |
| MobileLLaMA 1.4B Chatmtgv | — | 1.5 GB | ~426 | same size |
| EXAONE 4.0 1.2BLGAI-EXAONE | — | 2.1 GB | ~551 | same size |
Specifications
- Publisher
- Meta
- Parameters
- 1.3B
- Architecture
- OPTForCausalLM
- Context Length
- 2,048 tokens
- Vocabulary Size
- 50,272
- Release Date
- 2022-05-11
- License
- Other
Frequently Asked Questions
How much VRAM does Opt 1.3B need?
Opt 1.3B requires 2.9 GB of VRAM at FP16.
VRAM = Weights + KV Cache + Overhead
Weights = 1.3B × 16 bits ÷ 8 = 2.6 GB
KV Cache + Overhead ≈ 0.3 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.
VRAM usage by quantization
Can I run Opt 1.3B on a Mac?
Yes — Mac Mini M2 (8 GB) and 145 other Macs can run Opt 1.3B. Apple Silicon uses unified memory, so the model shares RAM with the system. At FP16 you need at least 2.9 GB of usable unified memory (RAM minus macOS overhead).
Can I run Opt 1.3B locally?
Yes — Opt 1.3B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Opt 1.3B?
At FP16, Opt 1.3B can reach ~1678 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~229 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 ÷ 2.86 × 0.65 = ~1818 tok/s
Estimated speed at FP16 (2.9 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Opt 1.3B?
At FP16, the download is about 2.60 GB.
Which GPUs can run Opt 1.3B?
52 consumer GPUs can run Opt 1.3B at FP16. 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 Opt 1.3B?
163 devices with unified memory can run Opt 1.3B at FP16 (2.9 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.