FitMyLLM
OpenAI/Dense

OpenAIGPT-2 Medium 345M

Medium GPT-2 variant. Useful for learning and experimentation, not production tasks.

chat
0.38B
Parameters
1K
Context length
6
Benchmarks
6
Quantizations
1.0M
HF downloads
Architecture
Dense
Released
2019-02-14
Layers
24
KV Heads
16
Head Dim
64
Family
gpt2

Quantization Options

QuantBitsVRAM @ 1KQuality
Q4_K_M4.89
0.7 GB
good
Q5_K_S5.57
0.8 GB
good
Q5_K_M5.7
0.8 GB
good
Q6_K6.56
0.8 GB
excellent
Q8_08.5
0.9 GB
lossless
FP1616
1.2 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 Medium 345M 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
$ollama run hf.co/ggml-org/gpt-2-GGUF:Q4_K_M

Not in Ollama's library: Ollama pulls the GGUF from Hugging Face (ggml-org/gpt-2-GGUF). If Q4_K_M is not in that repo, pick a file listed there.

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 Medium 345M

Build Hardware for GPT-2 Medium 345M

Medium GPT-2 variant. Useful for learning and experimentation, not production tasks.

Spec sheet

GPT-2 Medium 345M — 0.38B Dense.

Specifications
Parameters
0.38B
Architecture
Dense Transformer
Context Length
1K tokens
Capabilities
chat
Release Date
2019-02-14
Provider
OpenAI
Family
gpt2
VRAM requirements
QuantBPWVRAMQuality
Q4_K_M4.890.7 GB94%
Q5_K_S5.570.8 GB96%
Q5_K_M5.70.8 GB96%
Q6_K6.560.8 GB97%
Q8_08.50.9 GB100%
FP16161.2 GB100%
Benchmark scores
MMLU-PRO2.0
MATH0.8
IFEval22.1
BBH2.7
GPQA1.7
MUSR6.2
Compatible GPUs
30 @ Q4_K_M