TinyStories 33M — Hardware Requirements & GPU Compatibility
Chat
TinyStories 33M is a 33M-parameter open language model from roneneldan. It supports a context window of up to 2,048 tokens. At BF16 it needs about 0.07 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (BF16 · 2K)Best on 24 GB (BF16 · ~9360 tok/s · 2K)Macs from 8 GB (BF16 · ~1024 tok/s)
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run TinyStories 33M
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve roneneldan/TinyStories-33M --max-model-len 2048vLLM repo with its own quantisation
Download: Weights on Hugging Face
Other ways
each opens step-by-stepRun in cloud
Fits on RTX 3060 12GB (11 GB headroom) · BF16
- Generation speed
- ~3343 tok/s
- generation speed
- Cost per 1M output tokens
- $0.0057
- per 1M output tokens
How Much VRAM Does TinyStories 33M Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 0.1 GB | — | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 2K context · ~9360 tok/s |
Selected BF16
Brain floating point 160.1GBat 2K context
- Weights
- 0.1 GB
- KV cache
- 0.0 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 23.9 GB free · ~9360 tok/s
≥50 tok/s needs ≥5 GB/s · RTX 5090 ~16640, RTX 3090 Ti ~9360
Which Hardware Can Run TinyStories 33M?
BF16 · 0.1 GBTinyStories 33M (BF16) requires 0.1 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 1+ 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 TinyStories 33M, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 7.9 GB free · up to 2K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~7060Simulate output on RTX 3080RTX 2080 Ti~5720Simulate output on RTX 2080 TiRTX 3070 Ti~5649Simulate output on RTX 3070 TiM3*8 GB~1024Simulate output on iMac 24" M3 (8 GB)Orin Nano~947Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~682Simulate output on iPhone 1720 GB
fits · 19.9 GB free · up to 2K ctx
1 GPU
RX 7900 XT~6857Simulate output on RX 7900 XT32–40 GB
fits · 31.9 GB free · up to 2K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~16640Simulate output on RTX 5090M5 Max36 GB~4600Simulate output on Mac Studio M5 Max (36 GB)M532 GB~1536Simulate output on MacBook Air 13" M5 (32 GB)Orin~1902Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~1254Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at BF16
Specifications
- Publisher
- roneneldan
- Parameters
- 33M
- Architecture
- GPTNeoForCausalLM
- Context Length
- 2,048 tokens
- Vocabulary Size
- 50,257
- Release Date
- 2023-05-12
Frequently Asked Questions
How much VRAM does TinyStories 33M need?
TinyStories 33M requires 0.1 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 33M × 16 bits ÷ 8 = 0.1 GB
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 TinyStories 33M on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run TinyStories 33M. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 0.1 GB of usable unified memory (RAM minus macOS overhead).
Can I run TinyStories 33M locally?
Yes — TinyStories 33M can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is TinyStories 33M?
At BF16, TinyStories 33M can reach ~68571 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~9360 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 ÷ 0.07 × 0.65 = ~74286 tok/s
Estimated speed at BF16 (0.1 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of TinyStories 33M?
At BF16, the download is about 0.07 GB.
Which GPUs can run TinyStories 33M?
52 consumer GPUs can run TinyStories 33M 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 TinyStories 33M?
163 devices with unified memory can run TinyStories 33M at BF16 (0.1 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.