Google
ChatCodingReasoningMulti-purpose27.23B
Chat

Gemma 2 27B Instruct

Gemma · Gemma License

Google's 27B model with effective knowledge distillation. Reasoning and coding at a size that fits on a single 24 GB GPU at Q4. Limited to 8K context.

Parameters
27.23B
Architecture
Dense
Context
8,192 tokens
Released
2024-06-27
Engines
llama.cpp, ollama, vLLM

Parameters

27.23B

VRAM

18.5 GB

Context

8K

Formats

4

GPUs

21

Gemma 2 27B Instruct (27.23B) requires 18.5 GB VRAM at recommended quality (Q5_K_M). At efficient quality (Q4_K_M), it fits in 15.5 GB VRAM, making it compatible with the NVIDIA RTX 4090 Laptop (150-175W). On NVIDIA Grace Blackwell Ultra GB300, expect approximately 145 tok/s at Q5_K_M. For the best experience, AMD AI Powerhouse ($1,818) is recommended.

Source: OwnRig methodology

VRAM (Recommended)

18.5 GB

Quantization

Q5_K_M

File Size

16.3 GB

Max Context

8K tokens

Primary Use

Chat

Memory

VRAM Requirements

QualityQuantizationVRAMFile Size
recommendedQ5_K_M18.5 GB16.3 GB
efficientQ4_K_M15.5 GB13.6 GB
compressedQ3_K_M12.5 GB10.6 GB
compressedQ2_K9.8 GB8.2 GB
Scaling

Context Length Impact

KV cache VRAM at Q5_K_M quality. Longer context = more memory.

ContextKV CacheTotal VRAM
2K307 MB18.8 GB
4K614 MB19.1 GB
8K1.3 GB19.8 GB

Compatible GPUs

21 devices
NVIDIA Grace Blackwell Ultra GB300Q5_K_M145 tok/sExcellent
Apple M4 Max (36GB Unified)Q5_K_M15 tok/sGood
NVIDIA GeForce RTX 4090Q4_K_M22 tok/sGood
AMD Radeon RX 7900 XTXQ4_K_M19 tok/sGood
AMD Radeon Pro W7900Q4_K_M24 tok/sGood
NVIDIA RTX PRO 6000 BlackwellQ5_K_M59 tok/sGood
NVIDIA RTX PRO 6000 Blackwell Max-QQ5_K_M54 tok/sGood
NVIDIA GeForce RTX 4060 Ti 16GBQ4_K_M12 tok/sAcceptable
NVIDIA RTX 4090 Laptop (150-175W)Q4_K_M10 tok/sAcceptable
AMD Radeon RX 9070Q3_K_M22 tok/sAcceptable
AMD Radeon RX 9060 XT 16GBQ3_K_M11 tok/sAcceptable
NVIDIA GeForce RTX 5060 Ti 16GBQ4_K_M13 tok/sAcceptable
AMD Radeon RX 7600Q2_K2 tok/sMarginal
Apple M3 Pro (18GB Unified)Q4_K_MNot viable
NVIDIA GeForce RTX 3080 10GBQ3_K_MNot viable
NVIDIA GeForce RTX 4060 8GBQ3_K_MNot viable
NVIDIA RTX 4060 Laptop (40-60W)Q3_K_MNot viable
NVIDIA RTX 4070 Laptop (80-115W)Q3_K_MNot viable
NVIDIA GeForce RTX 4070 Ti 12GBQ3_K_MNot viable
AMD Radeon RX 9060 XT 8GBQ3_K_MNot viable
NVIDIA GeForce RTX 5060 8GBQ3_K_MNot viable

Showing 21 of 21 entries

Hardware

Recommended Builds

Complete PC builds that can run Gemma 2 27B Instruct.

FAQ

Frequently Asked Questions

How much VRAM does Gemma 2 27B Instruct need?
Gemma 2 27B Instruct requires 18.5 GB VRAM at recommended quality (Q5_K_M). At lower quality settings, it can fit in as little as 9.8 GB.
What is the best GPU for Gemma 2 27B Instruct?
The NVIDIA Grace Blackwell Ultra GB300 delivers the best performance for Gemma 2 27B Instruct, achieving 145 tok/s at Q5_K_M with an excellent rating.
Can I run Gemma 2 27B Instruct on an RTX 4060 Ti?
Yes. On the NVIDIA GeForce RTX 4060 Ti 16GB, Gemma 2 27B Instruct runs at 12 tok/s (Q4_K_M, acceptable).
What quantization should I use for Gemma 2 27B Instruct?
For the best quality, use Q5_K_M (18.5 GB VRAM). If your GPU has limited VRAM, Q2_K (9.8 GB) is the most efficient option with acceptable quality.
Is Gemma 2 27B Instruct good for coding?
Gemma 2 27B Instruct supports coding use cases. For the best coding experience, pair it with an embedding model for local RAG.
All models

Data confidence: verified. Source

VRAM requirements are calculated from model parameters and may vary by inference engine, context length, and batch size. Performance estimates are based on community benchmarks and should be verified for your specific configuration.Gemma is a trademark of its respective owner. OwnRig is not affiliated with or endorsed by the model creator.