on

Can the NVIDIA RTX Spark N1X (6144-core GPU) (32 GB) run ShieldGemma 27B?

62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.

Yes, but slowly (far over GPU memory limit)

Slow (far over GPU memory limit). At Q4_K_M it needs about 19.2 GB of 16.0 GB usable and makes one decision in about 762 ms.

Best quant
Q4_K_M
Time per decision
762 ms
Decisions per second
1.3/s
Input assumed
512 tokens
Returns
Probability or score

Best app to run it on the NVIDIA RTX Spark N1X (6144-core GPU) (32 GB)

On Linux

LM Studio

Desktop app · runs on llama.cpp, MLX

  • Splits the model between GPU memory and system RAM, which this setup needs.
  • Point-and-click: search, download and chat in one window.

Open ShieldGemma 27B in LM Studio

  • Ollama Splits the model between GPU memory and system RAM, which this setup needs.
  • llama.cpp 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 NVIDIA RTX Spark N1X (6144-core GPU) (32 GB): 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 1 day 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 52/100 (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 Slowfar over GPU memory limit
How well it runs on the NVIDIA RTX Spark N1X (6144-core GPU) (32 GB): 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 the model fits in the share of unified memory the GPU can use; fewer when it goes past that limit.4.0 / 25
SpeedTime for one decision against a 100 ms target: reading the input plus any tokens the model writes.5.4 / 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 score52.6 / 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 NVIDIA RTX Spark N1X (6144-core GPU) (32 GB)

Quant Memory needed Available Speed Runs Quality Download
Q4_K_M 19.2 GB 16.0 GB 762 ms Slowfar over GPU memory limit 62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q5_K_M 22.0 GB 16.0 GB — Won't run 64Good quality (B) · 64 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q6_K 25.0 GB 16.0 GB — Won't run 65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q8_0 31.5 GB 16.0 GB — Won't run 66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
F16 57.1 GB 16.0 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

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.

Was this page helpful?