Gemma 3 27B IT on NVIDIA RTX PRO 6000 Blackwell

Can the NVIDIA RTX PRO 6000 Blackwell run Gemma 3 27B IT?

80 pts

Yes, it runs well

Runs well. At Q8_0 it needs about 35.2 GB of 96.0 GB usable, with an estimated speed of 40.9 tok/s.

Best quant: Q8_0
Generation speed: 40.9 tok/s
Prompt processing: 3,285 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 128K

Download Gemma 3 27B IT

Recommended for the NVIDIA RTX PRO 6000 Blackwell: Q8_0. 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.

ollama run gemma3:27b-it-q8_0

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

Quantized files · GGUF

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

Download the Q8_0 file (opens in a new tab)

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:Q8_0

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)

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

Google DeepMind’s official Gemma library.

Links checked 1 week ago against Hugging Face, Ollama and GitHub.

How the A grade is scored

Every result gets up to 100 points from four parts. The points decide the letter grade.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	32.4 / 45
Memory fitFull marks when everything sits in GPU or unified 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.	8.5 / 15
Total	80.9 / 100	80 ptsGreat (A) · 80 of 100 points: Model quality 32.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.5/15

Grade scale: S 85+ · A 72+ · B 58+ · C 42+ · D 25+ · F under 25 points.

Every quantization on the NVIDIA RTX PRO 6000 Blackwell

Quant	Memory needed	Available	Speed	Fit	Grade · points	Download
`Q2_K`	17.2 GB	96.0 GB	132 tok/s	Runs well	66 ptsGood (B) · 66 of 100 points: Model quality 22.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.1/15	GGUF files (opens in a new tab)
`Q3_K_M`	19.6 GB	96.0 GB	104 tok/s	Runs well	71 ptsGood (B) · 71 of 100 points: Model quality 27.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.7/15	GGUF files (opens in a new tab)
`Q4_K_M`	22.9 GB	96.0 GB	80.3 tok/s	Runs well	76 ptsGreat (A) · 76 of 100 points: Model quality 30.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.5/15	GGUF (opens in a new tab)
`Q5_K_M`	25.7 GB	96.0 GB	66.3 tok/s	Runs well	77 ptsGreat (A) · 77 of 100 points: Model quality 31.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.2/15	GGUF files (opens in a new tab)
`Q6_K`	28.7 GB	96.0 GB	55.7 tok/s	Runs well	78 ptsGreat (A) · 78 of 100 points: Model quality 32.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.9/15	GGUF files (opens in a new tab)
`Q8_0`	35.2 GB	96.0 GB	40.9 tok/s	Runs well	80 ptsGreat (A) · 80 of 100 points: Model quality 32.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.5/15	GGUF (opens in a new tab)
`F16`	61.0 GB	96.0 GB	18.8 tok/s	Runs well	82 ptsGreat (A) · 82 of 100 points: Model quality 32.4/45, Memory fit 25.0/25, Speed 10.3/15, Memory use 14.7/15	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

87 ptsExcellent (S) · 87 of 100 points: Model quality 32.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 5090 Q6_K · 55.7 tok/s
85 ptsExcellent (S) · 85 of 100 points: Model quality 30.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 3090 Q4_K_M · 41.9 tok/s
85 ptsExcellent (S) · 85 of 100 points: Model quality 30.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4090 Q4_K_M · 45.2 tok/s
85 ptsExcellent (S) · 85 of 100 points: Model quality 30.8/45, Memory fit 25.0/25, Speed 14.4/15, Memory use 15.0/15 AMD Radeon RX 7900 XTX Q4_K_M · 37.0 tok/s
81 ptsGreat (A) · 81 of 100 points: Model quality 27.2/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4080 SUPER Q3_K_M · 42.6 tok/s
81 ptsGreat (A) · 81 of 100 points: Model quality 27.2/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 5070 Ti Q3_K_M · 51.9 tok/s

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.