Gemma 3 27B IT on NVIDIA A800 40GB Active

Can the NVIDIA A800 40GB Active run Gemma 3 27B IT?

Yes, it runs great

Runs great. At Q6_K it needs about 25.9 GB of 40.0 GB usable, with an estimated speed of 48.3 tok/s.

Best quant: Q6_K
Generation speed: 48.3 tok/s
Prompt processing: 512 tok/s
First token (1K prompt): 2.0 s
Largest safe context: 128K

Best app to run it on the NVIDIA A800 40GB Active

On Linux

vLLM

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-3-27b-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 gemma3:27b

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

Reverse engineering? Serve Gemma 3 27B IT locally and use it from Ghidra, IDA Pro, Binary Ninja, radare2 or JADX with one of these:

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 3 27B IT

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 gemma3:27b

Quantized files · GGUF

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

huggingface.co/ggml-org/gemma-3-27b-it-GGUF (opens in a new tab)

ollama run hf.co/ggml-org/gemma-3-27b-it-GGUF

Original weights · Hugging Face

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

huggingface.co/google/gemma-3-27b-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 2 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 71Great quality (A) · 71 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q6_K, 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 A800 40GB Active: 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.	32.1 / 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.	14.9 / 15
Match score	87.0 / 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 A800 40GB Active

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	14.4 GB	40.0 GB	114 tok/s	Runs great	50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q3_K_M`	16.8 GB	40.0 GB	90.1 tok/s	Runs great	60Good quality (B) · 60 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q4_K_M`	20.1 GB	40.0 GB	69.7 tok/s	Runs great	68Good quality (B) · 68 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	22.9 GB	40.0 GB	57.6 tok/s	Runs great	69Good quality (B) · 69 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q6_K`	25.9 GB	40.0 GB	48.3 tok/s	Runs great	71Great quality (A) · 71 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q8_0`	32.4 GB	40.0 GB	35.5 tok/s	Runs great	72Great quality (A) · 72 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	58.2 GB	40.0 GB	1.9 tok/s	Very slowheavy RAM offload	72Great quality (A) · 72 of 100: how capable the model is at F16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · part 1 of 2 (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

71Great quality (A) · 71 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Q6_K · 55.7 tok/s · Runs great
68Good quality (B) · 68 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3090 Q4_K_M · 41.9 tok/s · Runs great
68Good quality (B) · 68 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 Q4_K_M · 45.2 tok/s · Runs great
68Good quality (B) · 68 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX Q4_K_M · 37.0 tok/s · Runs great
60Good quality (B) · 60 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4080 SUPER Q3_K_M · 42.6 tok/s · Runs well (tight fit)
60Good quality (B) · 60 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5070 Ti Q3_K_M · 51.9 tok/s · Runs well (tight fit)

Quick answers

How much memory does Gemma 3 27B IT need on the NVIDIA A800 40GB Active?

At Q6_K it needs about 25.9 GB. The NVIDIA A800 40GB Active has 40.0 GB usable.

How fast is Gemma 3 27B IT on the NVIDIA A800 40GB Active?

About 48.3 tok/s at Q6_K, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Gemma 3 27B IT should I use on the NVIDIA A800 40GB Active?

Q6_K. 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.