FitMyLLM
OpenAI/Dense

OpenAIGPT-2 Medium 345M

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

chat
0.345B
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

QuantBitsVRAMQuality
Q4_K_M4.890.7 GBgood
Q5_K_S5.570.7 GBgood
Q5_K_M5.70.7 GBgood
Q6_K6.560.8 GBexcellent
Q8_08.50.9 GBlossless
FP16161.2 GBlossless

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

▸ READY TO RUN THIS?RENT BY THE HOUR

RENT A GPU AND RUN GPT-2 MEDIUM 345M NOW

Rent on RunPod →Or Vast.ai →

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

Community Ratings

Loading ratings...

Benchmarks (6)

IFEval22.1
MUSR6.2
BBH2.7
MMLU-PRO2.0
GPQA1.7
MATH0.8

Run this model

▸Easiest way to get started·Beginners
DOCS ↗
curl -fsSL https://ollama.com/install.sh | sh
$ollama run gpt2:0.345b-q4_K_M

Tag may need adjustment — check ollama.com/library/gpt2 for available tags.

▸ 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
HuggingFaceGGUF DownloadsBuild Hardware

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

AMD FireGL V7350
1 GB VRAM • 41.6 GB/s
AMD
AmazonNeweggeBayPCPartPicker
NVIDIA Quadro FX 5500
1 GB VRAM • 32.3 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA Quadro FX 5500 SDI
1 GB VRAM • 32.3 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
AMD Stream Processor
1 GB VRAM • 41.5 GB/s
AMD
AmazonNeweggeBayPCPartPicker
AMD FireGL V8600
1 GB VRAM • 111.1 GB/s
AMD
AmazonNeweggeBayPCPartPicker
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce 9600M GS
1 GB VRAM • 25.6 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce 9650M GT
1 GB VRAM • 25.6 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce 9800M GTS
1 GB VRAM • 51.2 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce 9800M GTX
1 GB VRAM • 51.2 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GTX 280
1 GB VRAM • 141.7 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GTX 285
1 GB VRAM • 159 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA Quadro FX 3700M
1 GB VRAM • 51.2 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA Quadro FX 3800M
1 GB VRAM • 64 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA Quadro FX 4700 X2
1 GB VRAM • 51.2 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
AMD FireStream 9250
1 GB VRAM • 63.5 GB/s
AMD
AmazonNeweggeBayPCPartPicker
AMD FirePro V8700
1 GB VRAM • 108.8 GB/s
AMD
AmazonNeweggeBayPCPartPicker
AMD Radeon HD 4570
1 GB VRAM • 8 GB/s
AMD
AmazonNeweggeBayPCPartPicker
AMD Radeon HD 4710
1 GB VRAM • 25.6 GB/s
AMD
AmazonNeweggeBayPCPartPicker
AMD Radeon HD 4730 OEM
1 GB VRAM • 25.3 GB/s
AMD
AmazonNeweggeBayPCPartPicker
AMD Radeon HD 4870 X2
1 GB VRAM • 115.2 GB/s
AMD
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce 210 OEM
1 GB VRAM • 6.4 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce 210 Rev. 2
1 GB VRAM • 6.4 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce G110M
1 GB VRAM • 11.2 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GT 120M
1 GB VRAM • 16 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GT 130M
1 GB VRAM • 25.6 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GT 140 OEM
1 GB VRAM • 57.6 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GT 220
1 GB VRAM • 22.4 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GT 220M
1 GB VRAM • 16 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GT 230M
1 GB VRAM • 25.3 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker

Find the best GPU for GPT-2 Medium 345M

Build Hardware for GPT-2 Medium 345M

Model Card

View on HuggingFace

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

▸ SPEC SHEET

GPT-2 Medium 345M — 0.345B Dense.

▸ SPECIFICATIONS
PARAMETERS
0.345B
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_S5.570.7 GB96%
Q5_K_M5.70.7 GB96%
Q6_K6.560.8 GB97%
Q8_08.50.9 GB100%
FP16161.2 GB100%
§ 01BENCHMARK SCORES
MMLU-PRO2.0
MATH0.8
IFEval22.1
BBH2.7
GPQA1.7
MUSR6.2
§ 03COMPATIBLE GPUs
30 @ Q4_K_M
AMD FireGL V7350
1 GB · 41.6 GB/s
NVIDIA Quadro FX 5500
1 GB · 32.3 GB/s
NVIDIA Quadro FX 5500 SDI
1 GB · 32.3 GB/s
AMD Stream Processor
1 GB · 41.5 GB/s
AMD FireGL V8600
1 GB · 111.1 GB/s
NVIDIA GeForce 9600 GT Mac Edition
1 GB · 17 GB/s
NVIDIA GeForce 9600M GS
1 GB · 25.6 GB/s
NVIDIA GeForce 9650M GT
1 GB · 25.6 GB/s
NVIDIA GeForce 9800M GTS
1 GB · 51.2 GB/s
NVIDIA GeForce 9800M GTX
1 GB · 51.2 GB/s
NVIDIA GeForce GTX 280
1 GB · 141.7 GB/s
NVIDIA GeForce GTX 285
1 GB · 159 GB/s
NVIDIA Quadro FX 3700M
1 GB · 51.2 GB/s
NVIDIA Quadro FX 3800M
1 GB · 64 GB/s
NVIDIA Quadro FX 4700 X2
1 GB · 51.2 GB/s