ShieldGemma 27B on AMD Radeon RX 9070 GRE

Can the AMD Radeon RX 9070 GRE run ShieldGemma 27B?

Yes, but slowly (heavy RAM offload)

Slow (heavy RAM offload). At Q6_K it needs about 24.3 GB of 12.0 GB usable and makes one decision in about 839 ms.

Best quant: Q6_K
Time per decision: 839 ms
Decisions per second: 1.2/s
Input assumed: 512 tokens
Returns: Probability or score

Best app to run it on the AMD Radeon RX 9070 GRE

On Windows

llama.cpp

Command line + local API · runs on llama.cpp

Splits the model between GPU memory and system RAM, which this setup needs.
Gives you direct control of how many layers sit on the GPU, the best way to squeeze a model that doesn’t quite fit.
Usually the first to support new model architectures.

llama-server -hf mradermacher/shieldgemma-27b-GGUF:Q6_K

LM Studio Splits the model between GPU memory and system RAM, which this setup needs.
Lemonade Splits the model between GPU memory and system RAM, which this setup needs.

On Linux

llama.cpp

Command line + local API · runs on llama.cpp

Splits the model between GPU memory and system RAM, which this setup needs.
Gives you direct control of how many layers sit on the GPU, the best way to squeeze a model that doesn’t quite fit.
Usually the first to support new model architectures.

llama-server -hf mradermacher/shieldgemma-27b-GGUF:Q6_K

LM Studio Splits the model between GPU memory and system RAM, which this setup needs.
Lemonade Splits the model between GPU memory and system RAM, which this setup needs.

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 AMD Radeon RX 9070 GRE: Q6_K. 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 Q6_K 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:Q6_K

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 65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 53/100 (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 Slowheavy RAM offload: How well it runs on the AMD Radeon RX 9070 GRE: 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.	29.4 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.	4.0 / 25
SpeedTime for one decision against a 100 ms target: reading the input plus any tokens the model writes.	5.2 / 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	53.6 / 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 AMD Radeon RX 9070 GRE

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q4_K_M`	18.6 GB	12.0 GB	624 ms	Slowheavy RAM offload	62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	21.3 GB	12.0 GB	728 ms	Slowheavy RAM offload	64Good quality (B) · 64 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	24.3 GB	12.0 GB	839 ms	Slowheavy RAM offload	65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	30.8 GB	12.0 GB	1.1 s	Slowheavy RAM offload	66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	56.4 GB	12.0 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 RX 9070 GRE 12GB?

At Q6_K it needs about 24.3 GB. The RX 9070 GRE 12GB has 12.0 GB usable.

How fast is ShieldGemma 27B on the RX 9070 GRE 12GB?

It makes one decision in about 839 ms at Q6_K, 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.