Gemma 2B — Hardware Requirements & GPU Compatibility
Chat
Gemma 2B is a 2.5B-parameter open language model from Google in the Gemma 2 family. At Q4_K_M it needs about 1.65 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 32K)Best on 24 GB (Q4_K_M · ~397 tok/s · 32K)Macs from 8 GB (Q4_K_M · ~43 tok/s)
Gemma Terms
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Gemma 2B
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
ollama run hf.co/MaziyarPanahi/gemma-2b-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 20.5 GB free · 16K context
Download: gemma-2b.Q4_K_M.gguf1.63 GBMaziyarPanahi
Other ways
each opens step-by-stepRun in cloud
Fits on RTX 3060 12GB (8 GB headroom) · Q4_K_M
- Generation speed
- ~142 tok/s
- generation speed
- Cost per 1M output tokens
- $0.16
- per 1M output tokens
How Much VRAM Does Gemma 2B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 1.2 GB | 5.1 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 32K context · ~560 tok/s | |
| 1.2 GB | 5.2 GB | 3-bit small — 3-bit small quantization | Fits: 32K context · ~542 tok/s | |
| 1.3 GB | 5.3 GB | 3-bit medium — 3-bit medium quantization | Fits: 32K context · ~489 tok/s | |
| 1.4 GB | 5.4 GB | 4-bit · legacy — 4-bit legacy quantization | Fits: 32K context · ~475 tok/s | |
| 1.6 GB | 5.6 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 32K context · ~397 tok/s | |
| 2.0 GB | 5.9 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 32K context · ~334 tok/s | |
| 2.3 GB | 6.2 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 32K context · ~289 tok/s | |
| 2.8 GB | 6.7 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 32K context · ~237 tok/s |
Selected Q4_K_M
4-bit medium quantization3.5GBat 16K context
- Weights
- 1.1 GB
- KV cache
- 2.1 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 20.5 GB free · ~397 tok/s
≥50 tok/s needs ≥127 GB/s · RTX 5090 ~706, RTX 3090 Ti ~397
Which Hardware Can Run Gemma 2B?
Q4_K_M · 1.6 GBGemma 2B (Q4_K_M) requires 1.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 3+ GB is recommended. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run Gemma 2B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 4.5 GB free · up to 32K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~300Simulate output on RTX 3080RTX 2080 Ti~243Simulate output on RTX 2080 TiRTX 3070 Ti~240Simulate output on RTX 3070 TiM3*8 GB~43Simulate output on iMac 24" M3 (8 GB)Orin Nano~40Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~29Simulate output on iPhone 1720 GB
fits · 16.5 GB free · up to 32K ctx
1 GPU
RX 7900 XT~291Simulate output on RX 7900 XT32–40 GB
fits · 28.5 GB free · up to 32K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~706Simulate output on RTX 5090M5 Max36 GB~195Simulate output on Mac Studio M5 Max (36 GB)M532 GB~65Simulate output on MacBook Air 13" M5 (32 GB)Orin~81Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~53Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
How good is Gemma 2B?
llmrun Score blends public benchmark boards into one number; 100 = the average open model.
Not enough data yet for an llmrun Score.
A Score needs results on enough independent boards. How the Composite Score is built
Benchmarks
The 6 boards that weigh most in the llmrun Score, of 10 with a result for this model; badges show who ran the test.
- MMLU-Pro
TIGER-LabIndependent
Independent15.8%
#134/145 open
- MMLU
Epoch AI · Feb 2024Lab-reported
Lab-reported42.3%
#68/85 open
- BIG-Bench Hard
Epoch AI · Feb 2024Lab-reported
Lab-reported35.2%
#32/38 open
- GSM8K
Epoch AI · Feb 2024Lab-reported
Lab-reported17.7%
#55/62 open
- HellaSwag
Epoch AI · Feb 2024Lab-reported
Lab-reported71.4%
#30/47 open
- ARC Challenge
Epoch AI · Feb 2024Lab-reported
Lab-reported42.1%
#39/56 open
Alternatives to Gemma 2B
Gemma 2 family · 20 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| MiniCPM5 2BOpenBMB | — | 2.5 GB | ~345 | same size |
| North Micro Vision InstructCohere | — | 7.1 GB | ~119 | same size |
| LFM2.5 2.6BLiquid AI | — | 2.3 GB | ~321 | same size |
| Granite 3.1 2B InstructIBM | — | 3.2 GB | ~329 | same size |
| Ouro 2.6B ThinkingByteDance | — | 12.1 GB | ~102 | same size |
| EXAONE 3.5 2.4B InstructLGAI-EXAONE | — | 3.4 GB | ~412 | same size |
Specifications
- Publisher
- Family
- Gemma 2
- Parameters
- 2.5B
- Release Date
- 2024-02-08
- License
- Gemma Terms
Frequently Asked Questions
How much VRAM does Gemma 2B need?
Gemma 2B requires 1.6 GB of VRAM at Q4_K_M, or 5.5 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 2.5B × 4.8 bits ÷ 8 = 1.5 GB
KV Cache + Overhead ≈ 0.1 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
What's the best quantization for Gemma 2B?
For Gemma 2B, Q4_K_M (1.6 GB) offers the best balance of quality and VRAM usage. Q5_0 (1.7 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 0.8 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Gemma 2B on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run Gemma 2B. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 1.6 GB of usable unified memory (RAM minus macOS overhead).
Can I run Gemma 2B locally?
Yes — Gemma 2B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Gemma 2B?
At Q4_K_M, Gemma 2B can reach ~2909 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~397 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 ÷ 1.65 × 0.65 = ~3152 tok/s
Estimated speed at Q4_K_M (1.6 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Gemma 2B?
At Q4_K_M, the download is about 1.50 GB. The full-precision BF16 version is 5.01 GB. The smallest option (IQ2_XXS) is 0.69 GB.
Which GPUs can run Gemma 2B?
52 consumer GPUs can run Gemma 2B at Q4_K_M. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 52 GPUs have plenty of headroom for comfortable inference.
Which devices can run Gemma 2B?
163 devices with unified memory can run Gemma 2B at Q4_K_M (1.6 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.