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/InternVL2 8B/on RTX 3080 12GB

Can it run?

Can RTX 3080 12GB run InternVL2 8B?

BGood

Runs well

Using Q4_K_M in Ollama

Capabilities:

Fit status

Runs well

Decode

142.0 tok/s

TTFT

1363 ms

Safe context

8K

Memory

8.5 GB / 12.0 GB

Memory breakdown

Weights4.9 GB
KV Cache1.3 GB
Runtime1.2 GB
Headroom1.2 GB

Performance by workload

WorkloadGradeFitDecodeTTFTContext
Agentic CodingBRuns well142.0 tok/s1983 ms8K
ChatBRuns well142.0 tok/s743 ms8K
CodingBRuns well142.0 tok/s1363 ms8K
RAGBRuns well142.0 tok/s2478 ms8K
ReasoningBRuns well142.0 tok/s1611 ms8K

Quantization options

How InternVL2 8B (8B params) fits at each quantization level on RTX 3080 12GB (12.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
3.1 GB
LowD35
Q3_K_S
3
3.9 GB
LowD36
NVFP4
4
4.5 GB
MediumD37
Q4_K_M
4
4.9 GB
MediumD38
Q5_K_M
5
5.8 GB
HighD39
Q6_K
6
6.6 GB
HighC41
Q8_0Best for your GPU
8
8.6 GB
Very HighC44
F16
16
16.4 GB
MaximumF0

Get started

Ollama
ollama run internvl2-8b
HuggingFace
huggingface-cli download internvl2-8b
See all results for RTX 3080 12GBSee all hardware for InternVL2 8B