Google DeepMind
Google DeepMind
Language model · United States ·Apr 2025

TxGemma 27B

Language Open (Restricted)
27B
Parameters

About TxGemma 27B

TxGemma 27B is an AI model developed by Google DeepMind, in the language category, released in 2025, made available as an open-weights model with 27B params.

On this page you'll find TxGemma 27B's full specifications. Review provider pricing and benchmark scores below, or compare TxGemma 27B head-to-head with other language models.

→ More models by Google DeepMind → All language models → AI benchmarks leaderboard

Links

Announcement ↗ Hugging Face ↗

Run TxGemma 27B locally — what to buy

Share this build ↗

Sized to what TxGemma 27B actually needs (~8k context at Q4), not to the biggest GPU: Good = cheapest that runs it, Better = best value, Best = most headroom. Speed is a hardware estimate; anything past ~120 tok/s is shown as instant.

Good
AMD Radeon RX 7900 XT
Consumer GPU · ~$899
~40.7 tok/s
Q4 · tight on context · up to 7k ctx
Runs with: ExLlamaV2, KoboldCpp, LM Studio
See full estimate →
Better
AMD Radeon RX 7900 XTX
Consumer GPU · ~$999
~48.9 tok/s
Q4 · fits full context · up to 8k ctx
Runs with: ExLlamaV2, KoboldCpp, LM Studio
See full estimate →
Best
NVIDIA GeForce RTX 5090
Consumer GPU · ~$1,999
~103.1 tok/s
Q4 · fits full context · up to 8k ctx
Runs with: ExLlamaV2, KoboldCpp, LM Studio
See full estimate →

Software support

·ExLlamaV2 ·KoboldCpp ·LM Studio ·MLX ·Ollama ·SGLang ·TensorRT-LLM ·llama.cpp ·vLLM ?KTransformers ?text-generation-webui

✓ measured · · compatible · — not supported. Informational only — speed is hardware-based.

Consumer GPU
13–103.1 tok/s
10 options →
Apple
16.3–43.4 tok/s
17 options →
Datacenter GPU
44–120+ tok/s
13 options →

Community

Would you run TxGemma 27B again?
No votes yet — be the first.
Did it run? — community reports by hardware

No reports yet. Own this model on some hardware? Be the first to confirm it runs.

Discussion

No comments yet. Start the discussion.

More models like TxGemma 27B

AI
DMind-1
 AI
COLLECTIVE-1
 AI
Cogito 1 series
 AI
Euler (Euler大模型)
· 2.5B
 AI
SmolLM-1.7B
· 1.7B
 AI
Llama-3-70B-Synthia-v3.5
· 70B

Frequently asked questions

What is TxGemma 27B? ▶

TxGemma 27B is an AI model developed by Google DeepMind, in the language category, released in 2025. It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created TxGemma 27B? ▶

TxGemma 27B was developed by Google DeepMind and released in 2025.

Is TxGemma 27B open source or proprietary? ▶

TxGemma 27B ships as an open-weights model: you can download and self-host the weights, though the licence may place some restrictions on use.

How much does TxGemma 27B cost? ▶

Pricing for TxGemma 27B depends on the provider. See the providers table on this page for the latest API rates.

How does TxGemma 27B perform on benchmarks? ▶

Benchmark scores for TxGemma 27B are listed on this page as they are published. You can compare it head-to-head with other models on the GenAIList compare tool.

No videos yet. Know a good one? Add it below.

Know a great video about TxGemma 27B?