Yes — with 6.2 GB to spare

Gemma 4 12B at Q4_K_M fits your GeForce RTX 4060 Ti 16 GB entirely on the GPU at 8K context, at an estimated 26 tokens per second. Past 107K the KV cache pushes it over — quantise the cache to q8_0, or step down a quantisation, to go longer.

Fully on GPU 8K context Q4_K_M · 6.7 GB Apache 2.0 Released 29 May 2026 Vision

The "unified" Gemma 4: text, image and audio in one 12B that fits a 12 GB card at Q4. 140+ languages.

What hardware do I need for Gemma 4 12B? →

The VRAM budget

weights 6.7 GB

Weights 6.7 GB KV cache @ 8K 0.81 GB Runtime overhead 0.6 GB Free 6.2 GB of 14.4 GB

Quantisation ladder

Quant	Weights	Total @ 8K	Max context	Tok/s	Quality	Fit
F16	22.4 GB	23.8 GB	—	~3.0	Reference	9.4 GB over
Q8_0	11.9 GB	13.3 GB	25K	15	−0.1% ppl	Long context
Q6_K	9.2 GB	10.6 GB	69K	19	−0.4% ppl	Long context
Q5_K_M	7.9 GB	9.3 GB	89K	22	−0.8% ppl	Long context
Q4_K_M	6.7 GB	8.2 GB	107K	26	−1.9% ppl	Recommended
Q3_K_M	5.5 GB	6.9 GB	128K	32	−5.4% ppl	Long context
Q2_K	4.7 GB	6.1 GB	140K	37	−15% ppl	Long context

Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it. This model interleaves sliding-window layers (1024 tokens, 8 of 48 layers global), which is why its cache barely grows with context.

How to run it

Ollama llama.cpp LM Studio vLLM

terminal

$ ollama pull gemma4:12b
$ OLLAMA_CONTEXT_LENGTH=8192 \
    ollama run gemma4:12b

The default. One binary, a model registry, an OpenAI-compatible port. More on Ollama.

01Download is 6.7 GB. Keep it on an SSD — a first load off a spinning disk takes minutes.

02Close anything else holding VRAM. A browser with hardware acceleration can sit on 1–2 GB.

03There is room to go to 107K context on this card.

See all models for this rig Compare with another model