NVIDIA L4 24GB: Specs & Local-AI Compatibility
Low-power 24GB inference card for efficient serving.
Specs
- Memory
- 24 GB
- Memory type
- GDDR6
- Bandwidth
- 300 GB/s
- Approx FP16
- 30 TFLOPS
- Architecture
- Ada Lovelace
- Process
- TSMC 4N
- Power
- 72 W
- Launch
- 2023
Models this chip can run
Open models graded for a single NVIDIA L4 24GB, best fit first.
- CodeLlama 13BCodeLlama · ~13B · 16K ctx · Llama Community License
Fits at Q8_0 (~14GB) with ~7.1GB headroom — about 1 concurrent instance.
Q8_0 · ~14GBRuns well - Gemma 3 12BGemma 3 · ~12B · 128K ctx · Gemma Terms of Use
Fits at Q8_0 (~13GB) with ~8.1GB headroom — about 1 concurrent instance.
Q8_0 · ~13GBRuns well - Mistral Nemo 12BMistral · ~12B · 128K ctx · Apache-2.0
Fits at Q8_0 (~13GB) with ~8.1GB headroom — about 1 concurrent instance.
Q8_0 · ~13GBRuns well - Gemma 2 9BGemma · ~9B · 8K ctx · Gemma Terms of Use
Fits at FP16 (~19GB) with ~2.1GB headroom — about 1 concurrent instance.
FP16 · ~19GBRuns well - Llama 3.1 8BLlama · ~8B · 128K ctx · Llama Community License
Fits at FP16 (~17GB) with ~4.1GB headroom — about 1 concurrent instance.
FP16 · ~17GBRuns well - Qwen3 8BQwen · ~8B · 128K ctx · Apache-2.0
Fits at FP16 (~17GB) with ~4.1GB headroom — about 1 concurrent instance.
FP16 · ~17GBRuns well - Granite 3 8BGranite · ~8B · 128K ctx · Apache-2.0
Fits at FP16 (~17GB) with ~4.1GB headroom — about 1 concurrent instance.
FP16 · ~17GBRuns well - DeepSeek-R1 Distill 8BDeepSeek · ~8B · 128K ctx · MIT
Fits at FP16 (~17GB) with ~4.1GB headroom — about 1 concurrent instance.
FP16 · ~17GBRuns well
Build a private AI Business OS on NVIDIA L4 24GB
Run your own AI agents on hardware you control — private by design, no per-seat data leaving your premises. BrainOutput helps you pick the right machine and turn it into a working AI Business OS.
Explore the AI Business OS