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/StableLM 2 12B/on RTX 4080 Super 16GB

Can it run?

Can RTX 4080 Super 16GB run StableLM 2 12B?

BGood

Runs well

Using Q5_K_M in llama.cpp

Capabilities:

Fit status

Runs well

Decode

72.1 tok/s

TTFT

2684 ms

Safe context

4K

Memory

13.0 GB / 16.0 GB

Memory breakdown

Weights8.6 GB
KV Cache1.9 GB
Runtime0.9 GB
Headroom1.6 GB

Performance by workload

WorkloadGradeFitDecodeTTFTContext
Agentic CodingCTight fit72.1 tok/s3905 ms4K
ChatBRuns well72.1 tok/s1464 ms4K
CodingBRuns well72.1 tok/s2684 ms4K
RAGCTight fit72.1 tok/s4881 ms4K
ReasoningBRuns well72.1 tok/s3173 ms4K

Quantization options

How StableLM 2 12B (12B params) fits at each quantization level on RTX 4080 Super 16GB (16.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
4.7 GB
LowD35
Q3_K_S
3
5.9 GB
LowD36
NVFP4
4
6.7 GB
MediumD37
Q4_K_M
4
7.3 GB
MediumD38
Q5_K_M
5
8.6 GB
HighD40
Q6_KBest for your GPU
6
9.8 GB
HighC42
Q8_0
8
12.8 GB
Very HighC43
F16
16
24.6 GB
MaximumF0

Get started

HuggingFace
huggingface-cli download stablelm-2-12b
See all results for RTX 4080 Super 16GBSee all hardware for StableLM 2 12B