DiffusionGemma 26B-A4B IT on NVIDIA GeForce RTX 4060 Ti 16GB

Can the NVIDIA GeForce RTX 4060 Ti 16GB run DiffusionGemma 26B-A4B IT?

83 pts

Yes, with little memory to spare

Tight fit. At Q3_K_M it needs about 14.5 GB of 16.0 GB usable, with an estimated speed of 57.1 tok/s.

Best quant: Q3_K_M
Generation speed: 57.1 tok/s
Prompt processing: 3,978 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 38K

Download DiffusionGemma 26B-A4B IT

Quantized files · GGUF

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

huggingface.co/unsloth/diffusiongemma-26B-A4B-it-GGUF (opens in a new tab)

ollama run hf.co/unsloth/diffusiongemma-26B-A4B-it-GGUF

Original weights · Hugging Face

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

huggingface.co/google/diffusiongemma-26B-A4B-it (opens in a new tab)

No sign-in needed.

Links checked 2 hours 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.	29.5 / 45
Memory fitFull marks when everything sits in GPU or unified memory; fewer when part spills to system RAM.	24.0 / 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.	15.0 / 15
Total	83.5 / 100	83 ptsGreat (A) · 83 of 100 points: Model quality 29.5/45, Memory fit 24.0/25, Speed 15.0/15, 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 4060 Ti 16GB

Quant	Memory needed	Available	Speed	Fit	Grade · points	Download
`Q2_K`	12.1 GB	16.0 GB	72.6 tok/s	Runs well	79 ptsGreat (A) · 79 of 100 points: Model quality 24.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	GGUF files (opens in a new tab)
`Q3_K_M`	14.5 GB	16.0 GB	57.1 tok/s	Tight fit	83 ptsGreat (A) · 83 of 100 points: Model quality 29.5/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15	GGUF files (opens in a new tab)
`Q4_K_M`	17.6 GB	16.0 GB	33.3 tok/s	Runs with offload	72 ptsGreat (A) · 72 of 100 points: Model quality 33.3/45, Memory fit 10.0/25, Speed 13.7/15, Memory use 15.0/15	GGUF (opens in a new tab)
`Q5_K_M`	20.1 GB	16.0 GB	20.9 tok/s	Runs with offload	69 ptsGood (B) · 69 of 100 points: Model quality 34.0/45, Memory fit 10.0/25, Speed 10.8/15, Memory use 15.0/15	GGUF (opens in a new tab)
`Q6_K`	23.0 GB	16.0 GB	14.6 tok/s	Heavy offload	62 ptsGood (B) · 62 of 100 points: Model quality 34.7/45, Memory fit 4.0/25, Speed 9.1/15, Memory use 15.0/15	GGUF (opens in a new tab)
`Q8_0`	29.2 GB	16.0 GB	8.7 tok/s	Heavy offload	61 ptsGood (B) · 61 of 100 points: Model quality 35.1/45, Memory fit 4.0/25, Speed 7.0/15, Memory use 15.0/15	GGUF (opens in a new tab)
`F16`	53.4 GB	16.0 GB	—	Won't run	10 ptsWon't run (F) · 10 of 100 points: Model quality 10.5/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GGUF (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

89 ptsExcellent (S) · 89 of 100 points: Model quality 34.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 5090 Q6_K · 191 tok/s
88 ptsExcellent (S) · 88 of 100 points: Model quality 35.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.8/15 NVIDIA RTX PRO 6000 Blackwell F16 · 64.5 tok/s
88 ptsExcellent (S) · 88 of 100 points: Model quality 34.7/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 AMD Radeon RX 7900 XTX Q6_K · 88.0 tok/s
88 ptsExcellent (S) · 88 of 100 points: Model quality 34.7/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 3090 Q6_K · 99.6 tok/s
88 ptsExcellent (S) · 88 of 100 points: Model quality 34.7/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4090 Q6_K · 107 tok/s
87 ptsExcellent (S) · 87 of 100 points: Model quality 34.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.5/15 Apple M4 Max (64 GB) Q6_K · 50.1 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.