Transformer 1.3B 100B — Hardware Requirements & GPU Compatibility
Chat
Transformer 1.3B 100B is a 1.4B-parameter open language model from fla-hub. It supports a context window of up to 2,048 tokens. At BF16 it needs about 3.00 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 · ~218 tok/s · 2K)Macs from 8 GB (BF16 · ~24 tok/s)
MIT
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Transformer 1.3B 100B
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 fla-hub/transformer-1.3B-100B --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) · BF16
- Generation speed
- ~198 tok/s
- generation speed
- Cost per 1M output tokens
- $0.17
- per 1M output tokens
How Much VRAM Does Transformer 1.3B 100B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 3 GB | — | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 2K context · ~218 tok/s |
Selected BF16
Brain floating point 163.0GBat 2K context
- Weights
- 2.5 GB
- KV cache
- 0.2 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 21.0 GB free · ~218 tok/s
≥50 tok/s needs ≥231 GB/s · RTX 5090 ~388, RTX 3090 Ti ~218
Which Hardware Can Run Transformer 1.3B 100B?
BF16 · 3 GBTransformer 1.3B 100B (BF16) requires 3 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 Transformer 1.3B 100B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 5.0 GB free · up to 2K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~165Simulate output on RTX 3080RTX 2080 Ti~134Simulate output on RTX 2080 TiRTX 3070 Ti~132Simulate output on RTX 3070 TiM3*8 GB~24Simulate output on iMac 24" M3 (8 GB)Orin Nano~22Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~16Simulate output on iPhone 1720 GB
fits · 17.0 GB free · up to 2K ctx
1 GPU
RX 7900 XT~160Simulate output on RX 7900 XT32–40 GB
fits · 29.0 GB free · up to 2K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~388Simulate output on RTX 5090M5 Max36 GB~107Simulate output on Mac Studio M5 Max (36 GB)M532 GB~36Simulate output on MacBook Air 13" M5 (32 GB)Orin~44Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~29Simulate 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 4.6 ThinkingOpenBMB | — | 1.5 GB | ~580 | same size |
| Inkling Small DSpark PreviewRadixArk | — | 1.5 GB | ~555 | same size |
| Granite 3.0 1B A400m InstructIBM | — | 1.3 GB | ~524 | same size |
| MobileLLaMA 1.4B Chatmtgv | — | 1.5 GB | ~426 | same size |
| Phi 1 5Microsoft | — | 0.9 GB | ~697 | same size |
| EXAONE 4.0 1.2BLGAI-EXAONE | — | 2.1 GB | ~551 | same size |
Specifications
- Publisher
- fla-hub
- Parameters
- 1.4B
- Architecture
- TransformerForCausalLM
- Context Length
- 2,048 tokens
- Vocabulary Size
- 32,000
- Release Date
- 2024-04-01
- License
- MIT
Frequently Asked Questions
How much VRAM does Transformer 1.3B 100B need?
Transformer 1.3B 100B requires 3 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 1.4B × 16 bits ÷ 8 = 2.7 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 Transformer 1.3B 100B on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run Transformer 1.3B 100B. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 3 GB of usable unified memory (RAM minus macOS overhead).
Can I run Transformer 1.3B 100B locally?
Yes — Transformer 1.3B 100B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Transformer 1.3B 100B?
At BF16, Transformer 1.3B 100B can reach ~1600 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~218 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 ÷ 3.0 × 0.65 = ~1733 tok/s
Estimated speed at BF16 (3 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Transformer 1.3B 100B?
At BF16, the download is about 2.73 GB.
Which GPUs can run Transformer 1.3B 100B?
52 consumer GPUs can run Transformer 1.3B 100B 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 Transformer 1.3B 100B?
163 devices with unified memory can run Transformer 1.3B 100B at BF16 (3 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.