Gemma 2 27B IT on NVIDIA GeForce RTX 4070 SUPER

Can the NVIDIA GeForce RTX 4070 SUPER run Gemma 2 27B IT?

54 pts

Yes, with part of the model in system RAM

Runs with offload. At Q2_K it needs about 13.8 GB of 12.0 GB usable, with an estimated speed of 17.8 tok/s.

Best quant: Q2_K
Generation speed: 17.8 tok/s
Prompt processing: 829 tok/s
First token (1K prompt): 1.2 s
Largest safe context: —

Download Gemma 2 27B IT

Recommended for the NVIDIA GeForce RTX 4070 SUPER: Q2_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.

ollama run gemma2:27b-instruct-q2_K

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 Q2_K file (opens in a new tab)

huggingface.co/bartowski/gemma-2-27b-it-GGUF (opens in a new tab)

ollama run hf.co/bartowski/gemma-2-27b-it-GGUF:Q2_K

Original weights · Hugging Face

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

huggingface.co/google/gemma-2-27b-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 7 days ago against Hugging Face, Ollama and GitHub.

How the C 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.	19.5 / 45
Memory fitFull marks when everything sits in GPU or unified memory; fewer when part spills to system RAM.	10.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	10.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	15.0 / 15
Total	54.5 / 100	54 ptsUsable (C) · 54 of 100 points: Model quality 19.5/45, Memory fit 10.0/25, Speed 10.0/15, Memory use 15.0/15

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

Every quantization on the NVIDIA GeForce RTX 4070 SUPER

Quant	Memory needed	Available	Speed	Fit	Grade · points	Download
`Q2_K`	13.8 GB	12.0 GB	17.8 tok/s	Runs with offload	54 ptsUsable (C) · 54 of 100 points: Model quality 19.5/45, Memory fit 10.0/25, Speed 10.0/15, Memory use 15.0/15	GGUF (opens in a new tab)
`Q3_K_M`	16.3 GB	12.0 GB	9.5 tok/s	Heavy offload	49 ptsUsable (C) · 49 of 100 points: Model quality 23.4/45, Memory fit 4.0/25, Speed 7.3/15, Memory use 15.0/15	GGUF (opens in a new tab)
`Q4_K_M`	19.5 GB	12.0 GB	5.7 tok/s	Heavy offload	51 ptsUsable (C) · 51 of 100 points: Model quality 26.5/45, Memory fit 4.0/25, Speed 5.7/15, Memory use 15.0/15	GGUF (opens in a new tab)
`Q5_K_M`	22.3 GB	12.0 GB	4.2 tok/s	Heavy offload	50 ptsUsable (C) · 50 of 100 points: Model quality 27.1/45, Memory fit 4.0/25, Speed 4.9/15, Memory use 15.0/15	GGUF (opens in a new tab)
`Q6_K`	25.2 GB	12.0 GB	3.2 tok/s	Heavy offload	50 ptsUsable (C) · 50 of 100 points: Model quality 27.6/45, Memory fit 4.0/25, Speed 4.3/15, Memory use 15.0/15	GGUF (opens in a new tab)
`Q8_0`	31.8 GB	12.0 GB	2.1 tok/s	Heavy offload	50 ptsUsable (C) · 50 of 100 points: Model quality 27.9/45, Memory fit 4.0/25, Speed 3.4/15, Memory use 15.0/15	GGUF (opens in a new tab)
`F16`	57.3 GB	12.0 GB	—	Won't run	8 ptsWon't run (F) · 8 of 100 points: Model quality 8.4/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	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

82 ptsGreat (A) · 82 of 100 points: Model quality 27.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 5090 Q6_K · 56.1 tok/s
81 ptsGreat (A) · 81 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 3090 Q4_K_M · 42.2 tok/s
81 ptsGreat (A) · 81 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4090 Q4_K_M · 45.5 tok/s
80 ptsGreat (A) · 80 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 14.5/15, Memory use 15.0/15 AMD Radeon RX 7900 XTX Q4_K_M · 37.3 tok/s
76 ptsGreat (A) · 76 of 100 points: Model quality 27.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.6/15 NVIDIA RTX PRO 6000 Blackwell Q8_0 · 41.2 tok/s
73 ptsGreat (A) · 73 of 100 points: Model quality 19.5/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 AMD Radeon RX 9070 XT Q2_K · 40.8 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.