Can MedGemma 1.5 4B IT run on the RX 7900 XTX?
Yes. At 8K context the best fit is F16, using about 8.4 GB of the 22.8 GB usable on the RX 7900 XTX. Estimated speed ceiling: ~124 tokens/sec.
+ 0.8 GB with image input. The figures on this page are for text only. Sending images also loads the vision projector (mmproj) file: F16 at 8K context then needs about 9.2 GB (still fits). Calculator with image input on.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) • | 2.7 GB Fits | 2.8 GB Fits | 3.2 GB Fits | 5.1 GB Fits | 555 |
| 3-bit (Q3_K_M) • | 3.0 GB Fits | 3.1 GB Fits | 3.6 GB Fits | 5.5 GB Fits | 457 |
| 4-bit (Q4_K_M) • | 3.4 GB Fits | 3.5 GB Fits | 4.0 GB Fits | 5.8 GB Fits | 386 |
| 5-bit (Q5_K_M) • | 3.7 GB Fits | 3.8 GB Fits | 4.3 GB Fits | 6.1 GB Fits | 339 |
| 6-bit (Q6_K) • | 4.1 GB Fits | 4.1 GB Fits | 4.6 GB Fits | 6.5 GB Fits | 301 |
| 8-bit (Q8_0) • | 4.9 GB Fits | 5.0 GB Fits | 5.5 GB Fits | 7.4 GB Fits | 232 |
| 16-bit (F16/BF16) • | 8.3 GB Fits | 8.4 GB Fits | 8.9 GB Fits | 10.7 GB Fits | 124 |
• real GGUF file size from unsloth/medgemma-1.5-4b-it-GGUF. Speed is a bandwidth ceiling (960 GB/s), not a benchmark. Methodology.
What fits instead
- Cheapest listed GPU that runs MedGemma 1.5 4B IT: Arc B580 (12 GB, launch MSRP $249) at F16, fully in VRAM at 8K context.
- Largest popular model that fits the RX 7900 XTX: GLM 4.7 Flash (31B, MoE) at Q4_K_M, about 18.3 GB at 8K context.
"Runs" and "fits" mean the whole model in GPU memory at 8K context (4-bit or better for the model pick). Prices are US launch MSRPs, not today's street prices. "Popular" means the 60 most-downloaded models we track.
More
MedGemma 1.5 4B IT on every GPU and Mac · Every model that runs on the RX 7900 XTX · Other models that fit 24 GB VRAM · Try other settings in the calculator
Guides: Best GPU for local LLMs by budget · Can I run gpt-oss, Llama 70B or Qwen3? · Mac vs PC for local LLMs
Data: Hugging Face Hub (google/medgemma-1.5-4b-it), AMD specs. Model data last checked 2026-11-18; refreshed hourly.