Will It Run AI
CalculatorModelsHardwareCompare
Product
  • Calculator
  • Compare
  • Tier List
Browse
  • Models
  • Hardware
  • Docs
About
  • Why It Works
  • What's New
  • Legal Notice
  • Privacy Policy

All estimates are approximations based on mathematical models and public specifications. Actual performance may vary. Do not make purchasing decisions based solely on these estimates.

Data sourced from Hugging Face, Ollama, and official model documentation. Model names and logos are trademarks of their respective owners.

© 2026 Will It Run AI — Fase Consulting Ibiza, S.L. (NIF: B57969656)

Home/CodeLlama 13B Instruct/on RTX 5080 16GB

Can it run?

Can RTX 5080 16GB run CodeLlama 13B Instruct?

BGood

Runs well

Using Q4_K_M in Ollama

Capabilities:

Fit status

Runs well

Decode

78.7 tok/s

TTFT

2460 ms

Safe context

16K

Memory

12.8 GB / 16.0 GB

Memory breakdown

Weights7.9 GB
KV Cache2.0 GB
Runtime1.2 GB
Headroom1.6 GB

Performance by workload

WorkloadGradeFitDecodeTTFTContext
Agentic CodingCTight fit78.7 tok/s3579 ms16K
ChatBRuns well78.7 tok/s1342 ms11K
CodingBRuns well78.7 tok/s2460 ms16K
RAGCTight fit78.7 tok/s4473 ms16K
ReasoningBRuns well78.7 tok/s2908 ms16K

Quantization options

How CodeLlama 13B Instruct (13B params) fits at each quantization level on RTX 5080 16GB (16.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
5.1 GB
LowD36
Q3_K_S
3
6.4 GB
LowD37
NVFP4
4
7.3 GB
MediumD39
Q4_K_M
4
7.9 GB
MediumD39
Q5_K_M
5
9.4 GB
HighC41
Q6_KBest for your GPU
6
10.7 GB
HighC43
Q8_0
8
13.9 GB
Very HighC44
F16
16
26.7 GB
MaximumF0

Get started

Ollama
ollama run codellama-13b-instruct
HuggingFace
huggingface-cli download codellama-13b-instruct
See all results for RTX 5080 16GBSee all hardware for CodeLlama 13B Instruct