Gemma 2 27B IT — Hardware Requirements & GPU Compatibility
Chat
Google Gemma 2 27B IT is a 27.2-billion parameter instruction-tuned model from Google's Gemma 2 generation. It is a text-only chat model optimized for conversational use, reasoning, and instruction following. Gemma 2 27B IT was one of the strongest openly available models in its size class at release. The model requires a GPU with at least 24GB of VRAM for quantized local inference. It is widely supported by popular inference engines and remains a strong choice for users seeking high-quality local chat without needing 70B-class hardware. Released under the Gemma license.
Runs well on a 24 GB GPU
Runs from 12 GB (IQ2_M · 8K)Best on 24 GB (Q4_K_M · ~37 tok/s · 8K)Macs from 16 GB (IQ2_M · ~14 tok/s)
Score 72.7#97 of 106 open#29 of 36 that fit 24 GBGemma Terms
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
llmrun Composite Score →
72.7
- 90% range 66.0–79.4
- #97 of 106 open models
- #29 of 36 that fit 24 GB
Run Gemma 2 27B IT
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
ollama run gemma2:27b-instruct-q4_K_MQ4_K_M fits fully on the RTX 4090 · 4.5 GB free · 8K context
Download: gemma-2-27b-it-Q4_K_M.gguf16.65 GBbartowski
Ways to runOther ways
each opens step-by-stepRun in cloud
Your own private copy · Q4_K_M · 24 GB GPU
- The easiest way to try this model
- Running in a few minutes, easy setup
- Chat right here or connect any app
$5+ bonus for new users
Runs on RTX 3090 (24 GB) (4 GB headroom) · Q4_K_M
- Generation speed
- ~34 tok/s
- generation speed
- Cost per 1M output tokens
- $1.39
- per 1M output tokens
How Much VRAM Does Gemma 2 27B IT Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 12.7 GB | — | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 8K context · ~52 tok/s | |
| 13.1 GB | — | 3-bit small — 3-bit small quantization | Fits: 8K context · ~50 tok/s | |
| 14.6 GB | — | 3-bit medium — 3-bit medium quantization | Fits: 8K context · ~45 tok/s | |
| 15.0 GB | — | 4-bit · legacy — 4-bit legacy quantization | Fits: 8K context · ~44 tok/s | |
| 18.0 GB | — | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 8K context · ~37 tok/s | |
| 21.3 GB | — | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 8K context · ~31 tok/s | |
| 24.7 GB | — | 6-bit, very good — 6-bit quantization, very good quality | Does not fit: needs 24.7 GB | |
| 29.9 GB | — | 8-bit, near-lossless — 8-bit quantization, near-lossless | Does not fit: needs 30 GB |
Selected Q4_K_M
4-bit medium quantization19.5GBat 8K context
- Weights
- 17.2 GB
- KV cache
- 2.1 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 4.5 GB free · ~37 tok/s
≥50 tok/s needs ≥1.38 TB/s · RTX 5090 ~65
Which Hardware Can Run Gemma 2 27B IT?
Q4_K_M · 18.0 GBGemma 2 27B IT (Q4_K_M) requires 18.0 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. 122 devices with unified memory can run Gemma 2 27B IT, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Mini M5 Pro (24 GB).
20 GB
fits · 0.5 GB free · up to 8K ctx
1 GPU
RX 7900 XT~27Simulate output on RX 7900 XT32–40 GB
fits · 12.5 GB free · up to 8K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~65Simulate output on RTX 5090M5 Max36 GB~18Simulate output on Mac Studio M5 Max (36 GB)M532 GB~6Simulate output on MacBook Air 13" M5 (32 GB)Orin~7Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~5Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
How good is Gemma 2 27B IT?
The llmrun Score merges 3 public benchmark boards into a single figure, where 100 represents the average for open models.
Score vs VRAM in the 24 GB tier
- Gemma 2 27B IT
- Other models
- Best Score for its VRAM
#29 of 36 that fit 24 GB
Each dot is a model at the best quant that fits a 24 GB GPU. The line steps up to the best Score available at each amount of VRAM; a dot below it is beaten by a model that needs no more memory.
Full 24 GB ranking →Benchmarks
Here are all 6 boards that have results for this model, sorted by their weight in the llmrun Score; badges show who ran the test.
- GPQA Diamond
Epoch AI · Jun 2024Independent
Independent36.5%
#76/100 open
- LMArena Text
LMArena · Oct 2026Arena
Arena1289.5
#113/188 open
- AIME 2024/2025
Epoch AI · Jun 2024Independent
Independent1.4%
#80/88 open
- MMLU-Pro
TIGER-LabIndependent
Independent56.5%
#62/146 open
- MATH Level 5
Epoch AI · Jun 2024Independent
Independent27.9%
#24/39 open
- MMLU
Epoch AI · Jun 2024Lab-reported
Lab-reported75.7%
#19/85 open
In the 24 GB class
36 models fit 24 GBSame Score, only models that fit 24 GB at their best quant: the ranking a 24 GB owner actually chooses from.
- #1
Qwen3.8 27BAlibaba
122.0
~38 tok/s · 17.9 GB
- #2
Qwen3.6 27BAlibaba
111.2
~38 tok/s · 17.9 GB
- #3
Qwen3.6 35B A3BAlibaba
106.8
~151 tok/s · 22.0 GB
- #4
Gemma 4 31B ITGoogle
106.7
~32 tok/s · 21.7 GB
- #5
Gemma 4 26B A4B ITGoogle
105.8
~171 tok/s · 16.5 GB
- #6
Qwen3.5 35B A3BAlibaba
105.8
~151 tok/s · 22.0 GB
Alternatives to Gemma 2 27B IT
Gemma 2 family · 21 models →Official models with an llmrun Score, each answering one question; numbers are at the best quant that fits a 24 GB GPU.
Best alternative at this size
Qwen3.8 27B
Alibaba
- 49.3 higher Score
- 1.6 GB less VRAM
- 1 tok/s faster
Score 122.0 · 17.9 GB · ~38 tok/s
Much faster, similar quality
Qwen3.6 35B A3B
Alibaba
- 34.1 higher Score
- 2.5 GB more VRAM
- 115 tok/s faster
Score 106.8 · 22 GB · ~151 tok/s
Fits in less VRAM
GPT OSS 20B
OpenAI
- 23.7 higher Score
- 6.4 GB less VRAM
- 153 tok/s faster
Score 96.4 · 13.1 GB · ~190 tok/s
Other vendor
Qwen3.6 27B
Alibaba
- 38.5 higher Score
- 1.6 GB less VRAM
- 1 tok/s faster
Score 111.2 · 17.9 GB · ~38 tok/s
Similar models
10| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Gemma 4 31B ITGoogle | 106.7 | 21.7 GB | ~32 | similar score |
| Gemma 4 26B A4B ITGoogle | 105.8 | 16.5 GB | ~171 | similar score |
| Qwen3.5 35B A3BAlibaba | 105.8 | 22 GB | ~151 | similar score |
| Qwen3.5 27BAlibaba | 103.8 | 17.9 GB | ~38 | similar score |
| Seed OSS 36B InstructByteDance-Seed | 102.5 | 22.8 GB | ~31 | similar score |
| Qwen3 30B A3B Thinking 2507Alibaba | 100.7 | 19.4 GB | ~173 | similar score |
| Phi 4Microsoft | 83.9 | 12.5 GB | ~69 | similar score |
| Gemma 3 12B ITGoogle | 74.2 | 10.9 GB | ~82 | similar score |
| Mistral Nemo Instruct 2407Mistral AI | 65.4 | 11 GB | ~81 | similar score |
| Qwen2.5 7B InstructAlibaba | 65.1 | 5.8 GB | ~131 | similar score |
Fine-tunes & variants(2)
Specifications
- Publisher
- Family
- Gemma 2
- Parameters
- 27.2B
- Context Length
- 8,192 tokens
- Release Date
- 2024-06-24
- License
- Gemma Terms
Frequently Asked Questions
How much VRAM does Gemma 2 27B IT need?
Gemma 2 27B IT requires 18.0 GB of VRAM at Q4_K_M, or 59.9 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 27.2B × 4.8 bits ÷ 8 = 16.3 GB
KV Cache + Overhead ≈ 1.7 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
VRAM usage by quantization
Can NVIDIA GeForce RTX 4090 run Gemma 2 27B IT?
Yes, at Q5_K_L (21.7 GB) or lower. Higher quantizations like Q6_K (24.7 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
What's the best quantization for Gemma 2 27B IT?
For Gemma 2 27B IT, Q4_K_M (18.0 GB) offers the best balance of quality and VRAM usage. Q4_K_L (18.3 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 8.2 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Gemma 2 27B IT on a Mac?
Yes — Mac Mini M2 Pro (16 GB) and 133 other Macs can run Gemma 2 27B IT, the smallest at IQ2_M. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 18.0 GB of usable unified memory (RAM minus macOS overhead), from Mac Mini M5 Pro (24 GB).
Can I run Gemma 2 27B IT locally?
Yes — Gemma 2 27B IT can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Gemma 2 27B IT?
At Q4_K_M, Gemma 2 27B IT can reach ~267 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 ÷ 18.0 × 0.65 = ~289 tok/s
Estimated speed at Q4_K_M (18.0 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Gemma 2 27B IT?
At Q4_K_M, the download is about 16.34 GB. The full-precision BF16 version is 54.45 GB. The smallest option (IQ2_XXS) is 7.49 GB.
Which GPUs can run Gemma 2 27B IT?
8 consumer GPUs can run Gemma 2 27B IT at Q4_K_M. Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX. 1 GPU has plenty of headroom for comfortable inference.
Which devices can run Gemma 2 27B IT?
122 devices with unified memory can run Gemma 2 27B IT at Q4_K_M (18.0 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (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.