ShieldGemma 27B on NVIDIA RTX PRO 4000 Blackwell SFF Edition

Can the NVIDIA RTX PRO 4000 Blackwell SFF Edition run ShieldGemma 27B?

Yes, but slowly

Slow. At Q4_K_M it needs about 19.2 GB of 24.0 GB usable and makes one decision in about 861 ms.

Best quant: Q4_K_M
Time per decision: 861 ms
Decisions per second: 1.2/s
Input assumed: 512 tokens
Returns: Probability or score

Best app to run it on the NVIDIA RTX PRO 4000 Blackwell SFF Edition

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 shieldgemma:27b

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

On Linux

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 shieldgemma:27b

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 ShieldGemma 27B

Recommended for the NVIDIA RTX PRO 4000 Blackwell SFF Edition: Q4_K_M. 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 shieldgemma:27b

Quantized files · GGUF

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

Download the Q4_K_M file (opens in a new tab)

huggingface.co/mradermacher/shieldgemma-27b-GGUF (opens in a new tab)

ollama run hf.co/mradermacher/shieldgemma-27b-GGUF:Q4_K_M

Original weights · Hugging Face

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

huggingface.co/google/shieldgemma-27b (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).

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

How it’s rated

Quality 62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q4_K_M, 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 Slow: How well it runs on the NVIDIA RTX PRO 4000 Blackwell SFF Edition: 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.

PrecisionEditorial precision tier from the model’s published benchmarks, scaled by the quantization or precision used.	28.2 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.	25.0 / 25
SpeedTime for one decision against a 100 ms target: reading the input plus any tokens the model writes.	5.1 / 15
ClarityHow easy the answer is to use in code: a probability or score earns the most, written feedback before a score the least.	15.0 / 15
Match score	73.3 / 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 RTX PRO 4000 Blackwell SFF Edition

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q4_K_M`	19.2 GB	24.0 GB	861 ms	Slow	62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	21.9 GB	24.0 GB	872 ms	Slowtight fit	64Good quality (B) · 64 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	24.9 GB	24.0 GB	923 ms	Slowoffloads to RAM	65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	31.4 GB	24.0 GB	1.2 s	Slowoffloads to RAM	66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	57.0 GB	24.0 GB	—	Won't run	66Good quality (B) · 66 of 100: how capable the model is at F16, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)

Times are for one request with a 512-token input and about 1 tokens written. Batching servers process many requests at once.

Other hardware that runs it

66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell Q8_0 · 183 ms · Runs well
65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Q6_K · 206 ms · Runs well
62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX Q4_K_M · 214 ms · Runs well
62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 Q4_K_M · 260 ms · Runs well
62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT Q4_K_M · 354 ms · Runs well (offloads to RAM)
66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA B200 Q8_0 · 130 ms · Runs great

Quick answers

How much memory does ShieldGemma 27B need on the NVIDIA RTX PRO 4000 Blackwell SFF Edition 24GB?

At Q4_K_M it needs about 19.2 GB. The NVIDIA RTX PRO 4000 Blackwell SFF Edition 24GB has 24.0 GB usable.

How fast is ShieldGemma 27B on the NVIDIA RTX PRO 4000 Blackwell SFF Edition 24GB?

It makes one decision in about 861 ms at Q4_K_M, an estimate from the hardware and the size of the model.

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.