FitMyLLM
Meta/Dense

MetaLlama 2 13B

Llama 2 13B — great balance of capability and hardware requirements.

chat
13B
Parameters
4K
Context length
13
Benchmarks
10
Quantizations
0
Architecture
Dense
Released
2023-07-18
Layers
40
KV Heads
40
Head Dim
128
Family
llama

Quantization Options

QuantBitsVRAM @ 4KQuality
Q3_K_M4
7.0 GB
low
Q3_K_L4.3
7.5 GB
moderate
IQ4_XS4.46
7.7 GB
moderate
Q4_K_S4.67
8.1 GB
moderate
Q4_K_M4.89
8.4 GB
good
Q5_K_S5.57
9.5 GB
good
Q5_K_M5.7
9.8 GB
good
Q6_K6.56
11.1 GB
excellent
Q8_08.5
14.3 GB
lossless
FP1616
26.5 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 Llama 2 13B now

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

Community Ratings

Loading ratings...

Benchmarks (13)

Run this model

Easiest way to get started·Beginners
Docs ↗
curl -fsSL https://ollama.com/install.sh | sh
$ollama run llama2:13b-chat-q4_K_M

Downloads and runs automatically. Add --verbose for speed stats.

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.

NVIDIA CMP 170HX 10 GB
10 GB VRAM • 1560 GB/s
NVIDIA
NVIDIA CMP 50HX
10 GB VRAM • 560 GB/s
NVIDIA
NVIDIA CMP 90HX
10 GB VRAM • 760 GB/s
NVIDIA
NVIDIA Tesla K40c
12 GB VRAM • 288 GB/s
NVIDIA
NVIDIA Tesla K40d
12 GB VRAM • 288 GB/s
NVIDIA
NVIDIA Tesla K40m
12 GB VRAM • 288 GB/s
NVIDIA

Find the best GPU for Llama 2 13B

Build Hardware for Llama 2 13B

Llama 2 13B — great balance of capability and hardware requirements.

Spec sheet

Llama 2 13B — 13B Dense.

Specifications
Parameters
13B
Architecture
Dense Transformer
Context Length
4K tokens
Capabilities
chat
Release Date
2023-07-18
Provider
Meta
Family
llama
VRAM requirements
QuantBPWVRAMQuality
Q3_K_M47.0 GB88%
Q3_K_L4.37.5 GB90%
IQ4_XS4.467.7 GB92%
Q4_K_S4.678.1 GB93%
Q4_K_M4.898.4 GB94%
Q5_K_S5.579.5 GB96%
Q5_K_M5.79.8 GB96%
Q6_K6.5611.1 GB97%
Q8_08.514.3 GB100%
FP161626.5 GB100%
Benchmark scores
HumanEval38.4
MMLU-PRO10.3
MATH1.4
IFEval39.8
BBH7.2
GPQA0.0
MUSR8.2
MBPP52.6
Arena Elo1078
LiveCodeBench9.8
AIME1.7
GPQA Diamond32.1
HLE4.7
Run command

Run Llama 2 13B locally with Ollama — needs 8.4 GB VRAM at Q4_K_M:

$ollama run llama2:13b
Compatible GPUs
30 @ Q4_K_M