Can the AMD Radeon RX 7900 XTX run Gemma 3 4B?

Radeon RX 7900 XTX × Gemma 3 4B8K context
YesRuns fully on the GPU
Memory at FP1610.3 GB of 24 GB
Weights 8.6 GBKV cache 1.1 GBRuntime 0.6 GB
QuantFP16Full quality
Memory10.3 GBof 24 GB usable
Speed~67tokens per second
  1. FP16
  2. Q8_0
  3. Q6_K
  4. Q5_K_M
  5. Q4_K_M
  6. Q3_K_M
  7. Q2_K

Yes. The AMD Radeon RX 7900 XTX can run Gemma 3 4B fully in VRAM at FP16 (full quality), using about 10.3 GB of the 24 GB available, at roughly 67 tokens/second.

Run it with Ollama

With Ollama installed, one command downloads and starts Gemma 3 4B:

ollama run gemma3:4b

Ollama's default download is Q4_K_M (about 4.3 GB here). You have room for FP16, which is full quality: pick that GGUF in LM Studio or from Hugging Face.

Run it in the cloud

No AMD Radeon RX 7900 XTX? Run Gemma 3 4B in the cloud.

Rent a cloud GPU by the hour. No upfront cost, stop any time.

Memory needed by quantization

At 8,192 tokens of context. The black line marks the 24 GB the AMD Radeon RX 7900 XTX can use.

QuantQualityMemoryFits?Speed
FP16Full quality10.3 GBFits~67 tok/s
Q8_0Near-lossless6.3 GBFits~126 tok/s
Q6_KExcellent5.3 GBFits~163 tok/s
Q5_K_MVery good4.8 GBFits~188 tok/s
Q4_K_MGood, most popular4.3 GBFits~221 tok/s
Q3_K_MNoticeably degraded3.8 GBFits~274 tok/s
Q2_KHeavily degraded3.4 GBFits~357 tok/s

Frequently asked questions

Can AMD Radeon RX 7900 XTX run Gemma 3 4B?

Yes. The AMD Radeon RX 7900 XTX can run Gemma 3 4B fully in VRAM at FP16 (full quality), using about 10.3 GB of the 24 GB available, at roughly 67 tokens/second.

How much VRAM does Gemma 3 4B need?

About 4.3 GB at Q4_K_M with 8,192 tokens of context, and about 10.3 GB at full FP16 precision.

How fast is Gemma 3 4B on the AMD Radeon RX 7900 XTX?

Roughly 67 tokens per second at FP16, estimated from the AMD Radeon RX 7900 XTX's 960 GB/s memory bandwidth.