Txgemma 27B Chat — Hardware Requirements & GPU Compatibility
Chat
Txgemma 27B Chat is a 27.2B-parameter open language model from Google in the Gemma 2 family. At BF16 it needs about 59.90 GB of VRAM — see which GPUs and Macs can run it below.
339 downloads
60 likesSpecifications
- Publisher
- Family
- Gemma 2
- Parameters
- 27.2B
- Release Date
- 2025-04-10
- License
- Other
Get Started
HuggingFace
How Much VRAM Does Txgemma 27B Chat Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 59.9 GB | — | 54.45 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run Txgemma 27B Chat?
BF16 · 59.9 GBTxgemma 27B Chat (BF16) requires 59.9 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 78+ GB is recommended. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run Txgemma 27B Chat?
BF16 · 59.9 GB8 devices with unified memory can run Txgemma 27B Chat, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Studio M4 Max (64 GB).
Runs great
— Plenty of headroom
Decent
— Enough memory, may be tightRelated Models
Frequently Asked Questions
- How much VRAM does Txgemma 27B Chat need?
Txgemma 27B Chat requires 59.9 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 27.2B × 16 bits ÷ 8 = 54.5 GB
KV Cache + Overhead ≈ 5.4 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
BF1659.9 GB- Can NVIDIA GeForce RTX 5090 run Txgemma 27B Chat?
No — Txgemma 27B Chat requires at least 59.9 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
- Can I run Txgemma 27B Chat on a Mac?
Txgemma 27B Chat requires at least 59.9 GB at BF16, 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 Txgemma 27B Chat locally?
Yes — Txgemma 27B Chat can run locally on consumer hardware. At BF16 quantization it needs 59.9 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Txgemma 27B Chat?
At BF16, Txgemma 27B Chat can reach ~49 tok/s on AMD Instinct MI300X. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: AMD Instinct MI300X → 5300 ÷ 59.9 × 0.55 = ~49 tok/s
Estimated speed at BF16 (59.9 GB)
~49 tok/s~36 tok/s~30 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Txgemma 27B Chat?
At BF16, the download is about 54.45 GB.
- Which GPUs can run Txgemma 27B Chat?
No single consumer GPU has enough VRAM to run Txgemma 27B Chat at BF16 (59.9 GB). Multi-GPU or professional hardware is required.
- Which devices can run Txgemma 27B Chat?
8 devices with unified memory can run Txgemma 27B Chat at BF16 (59.9 GB), including Mac Pro M2 Ultra (192 GB), Mac Studio M2 Ultra (192 GB), Mac Studio M4 Max (128 GB), Mac Studio M4 Max (64 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.