FitMyLLM
OpenAI/Dense

OpenAIGPT-2 Large 774M

Larger GPT-2. Can generate coherent text but outdated by modern standards.

chatThinking
0.81B
Parameters
1K
Context length
6
Benchmarks
6
Quantizations
500K
HF downloads
Architecture
Dense
Released
2019-02-14
Layers
36
KV Heads
20
Head Dim
64
Family
gpt2

Quantization Options

QuantBitsVRAM @ 1KQuality
Q4_K_M4.89
1.0 GB
good
Q5_K_S5.57
1.1 GB
good
Q5_K_M5.7
1.1 GB
good
Q6_K6.56
1.2 GB
excellent
Q8_08.5
1.3 GB
lossless
FP1616
2.1 GB
lossless

Select your GPU above to see speed estimates and compatibility for each quantization.

Deploying for a team or in production? Size GPUs, cost & scaling in Enterprise →
Ready to run this?Rent by the hour

Rent a GPU and run GPT-2 Large 774M now

Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.

Community Ratings

Loading ratings...

Benchmarks (6)

Run this model

Easiest way to get started·Beginners
Docs ↗
curl -fsSL https://ollama.com/install.sh | sh
$# GPT-2 Large 774M is not in Ollama's library, and we know no GGUF build of it

Search Hugging Face for a GGUF of it (https://huggingface.co/models?sort=trending&search=gpt2-large+GGUF), or use the vLLM tab with the original weights.

Setup guide
>_

Auto-setup with fitmyllm CLI

Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.

pip install fitmyllmthen run fitmyllmLearn more
Auto-detect GPULive tok/s in chatSpeed benchmarks9 inference engines

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

Find the best GPU for GPT-2 Large 774M

Build Hardware for GPT-2 Large 774M

Larger GPT-2. Can generate coherent text but outdated by modern standards.

Spec sheet

GPT-2 Large 774M — 0.81B Dense.

Specifications
Parameters
0.81B
Architecture
Dense Transformer
Context Length
1K tokens
Capabilities
chat
Release Date
2019-02-14
Provider
OpenAI
Family
gpt2
VRAM requirements
QuantBPWVRAMQuality
Q4_K_M4.891.0 GB94%
Q5_K_S5.571.1 GB96%
Q5_K_M5.71.1 GB96%
Q6_K6.561.2 GB97%
Q8_08.51.3 GB100%
FP16162.1 GB100%
Benchmark scores
MMLU-PRO1.6
MATH1.2
IFEval20.5
BBH3.3
GPQA1.2
MUSR5.7
Compatible GPUs
30 @ Q4_K_M