FitMyLLM
Meta/Dense

MetaCodeLlama 13B

CodeLlama 13B — stronger code generation with more parameters.

coding
13B
Parameters
16K
Context length
8
Benchmarks
10
Quantizations
0
Architecture
Dense
Released
2023-08-24
Layers
40
KV Heads
40
Head Dim
128
Family
llama

Quantization Options

Context length:
QuantBitsVRAM @ 16KQuality
Q3_K_M4
16.4 GB
7.0 + 9.4 KV
low
Q3_K_L4.3
16.9 GB
7.5 + 9.4 KV
moderate
IQ4_XS4.46
17.1 GB
7.7 + 9.4 KV
moderate
Q4_K_S4.67
17.5 GB
8.1 + 9.4 KV
moderate
Q4_K_M4.89
17.8 GB
8.4 + 9.4 KV
good
Q5_K_S5.57
18.9 GB
9.5 + 9.4 KV
good
Q5_K_M5.7
19.1 GB
9.8 + 9.4 KV
good
Q6_K6.56
20.5 GB
11.1 + 9.4 KV
excellent
Q8_08.5
23.7 GB
14.3 + 9.4 KV
lossless
FP1616
35.9 GB
26.5 + 9.4 KV
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 CodeLlama 13B now

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

Community Ratings

Loading ratings...

Benchmarks (8)

Run this model

Easiest way to get started·Beginners
Docs ↗
curl -fsSL https://ollama.com/install.sh | sh
$ollama run codellama:13b-code-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 CodeLlama 13B

Build Hardware for CodeLlama 13B

CodeLlama 13B — stronger code generation with more parameters.

Spec sheet

CodeLlama 13B — 13B Dense.

Specifications
Parameters
13B
Architecture
Dense Transformer
Context Length
16K tokens
Capabilities
coding
Release Date
2023-08-24
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
Run command

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

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