Medgemma 27B Text IT — Hardware Requirements & GPU Compatibility
Chat
Google MedGemma 27B Text IT is a 27-billion parameter instruction-tuned model specialized for the medical domain, built on the Gemma architecture by Google. It is fine-tuned on medical and clinical text data to provide improved performance on healthcare-related tasks such as medical question answering, clinical reasoning, and health information summarization. The model requires a GPU with at least 24GB of VRAM for quantized inference. Its domain specialization makes it notably more capable than general models on clinical benchmarks, though it should not be used as a substitute for professional medical advice. Released under the Gemma license.
26.0K downloads
440 likesSpecifications
- Publisher
- Family
- Gemma
- Parameters
- 27.0B
- Release Date
- 2025-05-19
- License
- Other
Get Started
HuggingFace
How Much VRAM Does Medgemma 27B Text IT Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 12.6 GB | — | 11.48 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 13 GB | — | 11.82 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 14.5 GB | — | 13.17 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 14.8 GB | — | 13.50 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 17.8 GB | — | 16.21 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 21.2 GB | — | 19.24 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 24.5 GB | — | 22.28 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 29.7 GB | — | 27.01 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run Medgemma 27B Text IT?
Q4_K_M · 17.8 GBMedgemma 27B Text IT (Q4_K_M) requires 17.8 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 24+ GB is recommended. 8 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroom
Which Devices Can Run Medgemma 27B Text IT?
Q4_K_M · 17.8 GB41 devices with unified memory can run Medgemma 27B Text IT, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 Pro (24 GB).
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightWhere to Download Medgemma 27B Text IT
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Related Models
Frequently Asked Questions
- How much VRAM does Medgemma 27B Text IT need?
Medgemma 27B Text IT requires 17.8 GB of VRAM at Q4_K_M, or 59.4 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 27.0B × 4.8 bits ÷ 8 = 16.2 GB
KV Cache + Overhead ≈ 1.6 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
Q4_K_M17.8 GB- Can NVIDIA GeForce RTX 4090 run Medgemma 27B Text IT?
Yes, at Q5_K_M (21.2 GB) or lower. Higher quantizations like Q6_K (24.5 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
- What's the best quantization for Medgemma 27B Text IT?
For Medgemma 27B Text IT, Q4_K_M (17.8 GB) offers the best balance of quality and VRAM usage. Q5_0 (18.6 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 8.2 GB.
VRAM requirement by quantization
IQ2_XXS8.2 GBQ3_K_M14.5 GBQ4_K_S16.7 GBQ4_K_M ★17.8 GBQ5_K_S20.4 GBBF1659.4 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Medgemma 27B Text IT on a Mac?
Medgemma 27B Text IT requires at least 8.2 GB at IQ2_XXS, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run Medgemma 27B Text IT locally?
Yes — Medgemma 27B Text IT can run locally on consumer hardware. At Q4_K_M quantization it needs 17.8 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Medgemma 27B Text IT?
At Q4_K_M, Medgemma 27B Text IT can reach ~247 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~37 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 17.8 × 0.65 = ~292 tok/s
Estimated speed at Q4_K_M (17.8 GB)
~292 tok/s~37 tok/s~292 tok/s~247 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Medgemma 27B Text IT?
At Q4_K_M, the download is about 16.21 GB. The full-precision BF16 version is 54.02 GB. The smallest option (IQ2_XXS) is 7.43 GB.
- Which GPUs can run Medgemma 27B Text IT?
8 consumer GPUs can run Medgemma 27B Text IT at Q4_K_M (17.8 GB). Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX. 1 GPU have plenty of headroom for comfortable inference.
- Which devices can run Medgemma 27B Text IT?
41 devices with unified memory can run Medgemma 27B Text IT at Q4_K_M (17.8 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB), Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.