Skip to content
Run LLM Locally

Gemma 3 12B IT on the RX 7900 GRE

With 16 GB of VRAM, the RX 7900 GRE runs Gemma 3 12B IT at Q4_K_M entirely on the GPU with an 8K context (about 9.1 GB needed). At Q8_0 it fits entirely.

ShareFacebookXWhatsAppLinkedInEmail

Gemma 3 12B IT

Q4_K_M · 8K context

Excellent

The model needs about 9.1 GB and fits in the 15.5 GB available, with 6.4 GB to spare.

Your hardware
RX 7900 GRE 16 GB · 64 GB RAM
Estimated memory
~9.1 GB estimate
VRAM (usable memory)
15.5 GB
GPU only
Yes
CPU/GPU offload
Not required
Generation speed
42–62 tok/s estimate
Largest context in fast memory
105K tokens
Confidence: low

Based on: memory bandwidth (576 GB/s) and model size

Memory breakdown

~9.1 GB (8.5 GB–9.7 GB) needed · estimate

Fits entirely in VRAM · 6.4 GB left

  • Model weights6.8 GB
  • KV cache0.8 GB
  • Runtime overhead1.1 GB
  • Safety margin0.4 GB
Assumptions: context 8K tokens · KV cache f16 · llama.cpp (ROCm) · flash attention on · weights = real file size · sliding-window layers keep 1,024 tokens

EstimateData updated 24 days agoSource: Run LLM Locally engine, Hugging Face config.json + model card

What makes this estimate less reliable

  • no benchmark for this hardware and model yet

Other quantizations on the RX 7900 GRE

Gemma 3 12B IT on RX 7900 GRE + 64 GB RAM · 8K context
Gemma 3 12B IT Q8_08K~14.2 GB · 27–39 tok/s estimateCompatible
Gemma 3 12B IT Q6_K8K~11.4 GB · 34–49 tok/s estimateExcellent
Gemma 3 12B IT Q5_K_M8K~10.2 GB · 38–55 tok/s estimateExcellent
Gemma 3 12B IT Q4_K_M8K~9.1 GB · 42–62 tok/s estimateExcellent
Gemma 3 12B IT IQ4_XS8K~8.4 GB · 46–68 tok/s estimateExcellent
Gemma 3 12B IT Q3_K_M8K~7.8 GB · 49–73 tok/s estimateExcellent

Alternatives

GPUs that run Gemma 3 12B IT Q4_K_M entirely in VRAM

Other models that fit the RX 7900 GRE

Where to buy a RX 7900 GRE

Prices and links follow the market you choose.

Radeon RX 7900 GRE

16 GB GDDR6 · 576 GB/s · 260 W

ExcellentRuns Gemma 3 12B IT Q4_K_M entirely in memory

Price not available

Availability unknown

View on amazon.com

Affiliate link

No current offer imported for this market: the link opens a marketplace search.

Frequently asked questions

Can the RX 7900 GRE run Gemma 3 12B IT?
The model needs about 9.1 GB and fits in the 15.5 GB available, with 6.4 GB to spare.
Which quantization should I use on the RX 7900 GRE?
Q8_0 is the highest-precision quantization that fits entirely in VRAM at 8K context. ~14.2 GB / 15.5 GB.
What is the largest context on the RX 7900 GRE?
At Q4_K_M, about 105K tokens fit entirely in VRAM with an f16 KV cache. A q8_0 KV cache roughly doubles that.
How fast is Gemma 3 12B IT (RX 7900 GRE)?
We estimate 42–62 tok/s (estimate, confidence low). Based on: memory bandwidth (576 GB/s) and model size.