Gemma-4-31B-IT on NVIDIA L40S 48GB: VRAM Requirement & Speed Estimate
Yes. At Q4_K_M 4-bit quantization with a 16K context window, Gemma-4-31B-IT requires 22.47 GB of VRAM (18.61 GB weights + 2.18 GB KV cache + 1.67 GB overhead), fitting within L40S 48G's 47 GB usable memory at ~31.6 tokens/s.
Physical 48 GB · Load 47.8%
Actual speed varies ~±25% by runtime
Enable Q8/Q4 KV quantization to scale batch concurrency
OLLAMA_CONTEXT_LENGTH=16384 ollama run gemma4:31bL40S 48G Fits Gemma-4-31B-IT · Cost & TCO
Approx. $7,500 (~$156/GB VRAM) · 350W TDP
📊 All Quantization Levels for Gemma-4-31B-IT on L40S 48G
| Quantization | Total VRAM (16K) | Verdict | Est. Speed | Max Context |
|---|---|---|---|---|
| FP16 / BF16 | 66.11 GB | Partial RAM Offload (Slow) | ~3 tok/s | — |
| FP8 / Q8_0 | 36.75 GB | Smooth Fit | ~18.5 tok/s | 138K |
| GGUF Q6_K | 29.16 GB | Smooth Fit | ~23.7 tok/s | 229K |
| GGUF Q5_K_M | 25.75 GB | Smooth Fit | ~27.1 tok/s | 256K |
| Q4_K_M / AWQ | 22.47 GB | Smooth Fit | ~31.6 tok/s | 256K |
| GGUF IQ4_XS | 20.12 GB | Smooth Fit | ~35.8 tok/s | 256K |
| GGUF Q3_K_M | 18.79 GB | Smooth Fit | ~38.7 tok/s | 256K |
| GGUF Q2_K | 15.81 GB | Smooth Fit | ~47.2 tok/s | 256K |
💡 Recommended Alternative GPUs & Macs for Gemma-4-31B-IT
Frequently Asked Questions
Can NVIDIA L40S 48GB run Gemma-4-31B-IT locally?
Yes. At Q4_K_M 4-bit quantization with a 16K context window, Gemma-4-31B-IT requires 22.47 GB of VRAM (18.61 GB weights + 2.18 GB KV cache + 1.67 GB overhead), fitting within L40S 48G's 47 GB usable memory at ~31.6 tokens/s.
What is the best quantization for Gemma-4-31B-IT on L40S 48G?
The highest-quality quantization that fits cleanly on L40S 48G is FP8 / Q8_0 (99.9% Near-Lossless), using 36.75 GB VRAM at ~18.5 tokens/s with up to 138K context.
How much VRAM does Gemma-4-31B-IT need in full FP16 precision?
In unquantized FP16/BF16 precision (16K context), Gemma-4-31B-IT requires 66.11 GB VRAM (61.4 GB for weights alone).