Can the NVIDIA L40 run Gemma 3n E4B?

Yes, it runs great

Runs great. At F16 it needs about 18.8 GB of 48.0 GB usable, with an estimated speed of 62.2 tok/s.

Best quant: F16
Generation speed: 62.2 tok/s
Prompt processing: 16,290 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 32K

Best app to run it on the NVIDIA L40

On Linux

Inference server · runs on vLLM

The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.

vllm serve google/gemma-3n-E4B-it

Ollama One command with Ollama’s own build of this model.
LM Studio Point-and-click: search, download and chat in one window.

On Windows

Ollama

Command line + local API · runs on llama.cpp (ggml), MLX (Apple silicon, preview)

One command with Ollama’s own build of this model.
Serves an OpenAI-compatible API that other apps and coding tools can use.

ollama run gemma3n:e4b-it-fp16

LM Studio Point-and-click: search, download and chat in one window.
llama.cpp Usually the first to support new model architectures.

How we choose: the files published for this model, your operating system and GPU, whether it fits fully in memory, and published speed tests (MLX vs llama.cpp on Apple silicon, vLLM vs llama.cpp vs Ollama on NVIDIA). Details.

Download Gemma 3n E4B

Recommended for the NVIDIA L40: F16. Every other quantization has its own download link in the table below.

Quickest · Ollama

One command downloads a ready-to-run version and starts a chat.

Get Ollama at ollama.com/download (opens in a new tab) · model page (opens in a new tab)

ollama run gemma3n:e4b-it-fp16

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

Download the F16 file (opens in a new tab)

huggingface.co/unsloth/gemma-3n-E4B-it-GGUF (opens in a new tab)

ollama run hf.co/unsloth/gemma-3n-E4B-it-GGUF:F16

Original weights · Hugging Face

Full-precision files from Google, for fine-tuning, vLLM, Transformers.

huggingface.co/google/gemma-3n-E4B-it (opens in a new tab)

Free Hugging Face account needed: request access on the model page, and Google approves it (usually within minutes to a few hours).

Official repo · GitHub

Reference code, inference scripts and docs from Google. The weights themselves download from Hugging Face.

github.com/google-deepmind/gemma (opens in a new tab)

Google DeepMind’s official Gemma library.

git clone https://github.com/google-deepmind/gemma

Links checked 3 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 46Fair quality (C) · 46 of 100: how capable the model is at F16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at F16, from its editorial quality tier scaled by the quantization or precision. It’s the same on any hardware that runs this variant. Scale: A+ 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Runs great: How well it runs on the NVIDIA L40: speed, capped by how well it fits in memory. Runs great: 30+ tokens/s (or near the image, video or decision speed target) · Runs well: 10+ tokens/s · Slow: 3+ tokens/s · Very slow: under 3 · Won’t run: doesn’t fit even with offload. A tight fit or RAM offload caps it at Runs well; heavy offload caps it at Slow.

Match score

To order lists, each result also gets a match score out of 100 from four parts. It favors the most capable model that still runs well.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	20.7 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.	25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	15.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	9.1 / 15
Match score	69.8 / 100

The match score orders results; it is not shown as a grade. Quality and Runs are the two ratings in the tables.

Every quantization on the NVIDIA L40

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	6.3 GB	48.0 GB	435 tok/s	Runs great	32Basic quality (D) · 32 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	7.0 GB	48.0 GB	343 tok/s	Runs great	38Basic quality (D) · 38 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	7.9 GB	48.0 GB	265 tok/s	Runs great	43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	8.7 GB	48.0 GB	219 tok/s	Runs great	44Fair quality (C) · 44 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	9.6 GB	48.0 GB	184 tok/s	Runs great	45Fair quality (C) · 45 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	11.5 GB	48.0 GB	135 tok/s	Runs great	46Fair quality (C) · 46 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	18.8 GB	48.0 GB	62.2 tok/s	Runs great	46Fair quality (C) · 46 of 100: how capable the model is at F16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab) Original weights (opens in a new tab)

Memory figures assume 8K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

46Fair quality (C) · 46 of 100: how capable the model is at F16, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX F16 · 59.5 tok/s · Runs great
46Fair quality (C) · 46 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. Intel Arc B580 Q8_0 · 54.4 tok/s · Runs great
46Fair quality (C) · 46 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3060 12GB Q8_0 · 56.2 tok/s · Runs great
46Fair quality (C) · 46 of 100: how capable the model is at F16, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3090 F16 · 67.4 tok/s · Runs great
46Fair quality (C) · 46 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 SUPER Q8_0 · 78.7 tok/s · Runs great
46Fair quality (C) · 46 of 100: how capable the model is at F16, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 F16 · 72.6 tok/s · Runs great

Quick answers

How much memory does Gemma 3n E4B need on the NVIDIA L40 48GB?

At F16 it needs about 18.8 GB. The NVIDIA L40 48GB has 48.0 GB usable.

How fast is Gemma 3n E4B on the NVIDIA L40 48GB?

About 62.2 tok/s at F16, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Gemma 3n E4B should I use on the NVIDIA L40 48GB?

F16. Of the versions that fit, it is the one that runs best; when two run equally well, the check prefers the higher-rated one.

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.