Gemma 3 4B IT — Hardware Requirements & GPU Compatibility
Vision
Gemma 3 4B IT is a small, roughly 4.3-billion-parameter model from Google's earlier Gemma 3 generation, tuned for instruction-following and chat. It accepts image input alongside text, so it can handle visual question answering and image-grounded prompts in addition to text-only conversation. At this size, the model is comfortable on modest consumer hardware, running even on integrated graphics at low quantization, making it one of the most accessible vision-capable models for local use. Released on February 20, 2025, Gemma 3 4B IT predates the Gemma 4 family and is distributed under Google's Gemma license terms rather than a standard open-source license. Its compact size and image-input support make it a practical choice for lightweight, on-device multimodal applications.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 32K)Best on 24 GB (Q4_K_M · ~231 tok/s · 32K)Macs from 8 GB (Q4_K_M · ~25 tok/s)
Score 64#97 of 100 open#33 of 35 that fit 24 GBGemma Terms
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
llmrun Composite Score →
64.0
- 90% range 56.8–71.3
- #97 of 100 open models
- #33 of 35 that fit 24 GB
Run Gemma 3 4B IT
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
ollama run gemma3:4bQ4_K_M fits fully on the RTX 4090 · 19.0 GB free · 16K context
Download: gemma-3-4b-it.Q4_K_M.gguf2.49 GBMaziyarPanahi
Other ways
each opens step-by-stepRun in cloud
Fits on RTX 3060 12GB (7 GB headroom) · Q4_K_M
- Generation speed
- ~82 tok/s
- generation speed
- Cost per 1M output tokens
- $0.32
- per 1M output tokens
How Much VRAM Does Gemma 3 4B IT Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 2.0 GB | 6.6 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 32K context · ~326 tok/s | |
| 2.1 GB | 6.7 GB | 3-bit small — 3-bit small quantization | Fits: 32K context · ~317 tok/s | |
| 2.3 GB | 6.9 GB | 3-bit medium — 3-bit medium quantization | Fits: 32K context · ~284 tok/s | |
| 2.4 GB | 7 GB | 4-bit · legacy — 4-bit legacy quantization | Fits: 32K context · ~277 tok/s | |
| 2.8 GB | 7.5 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 32K context · ~231 tok/s | |
| 3.4 GB | 8 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 32K context · ~194 tok/s | |
| 3.9 GB | 8.5 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 32K context · ~168 tok/s | |
| 4.7 GB | 9.4 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 32K context · ~139 tok/s |
Selected Q4_K_M
4-bit medium quantization5.0GBat 16K context
- Weights
- 2.2 GB
- KV cache
- 2.5 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 19.0 GB free · ~231 tok/s
≥50 tok/s needs ≥218 GB/s · RTX 5090 ~410, RTX 3090 Ti ~231
Which Hardware Can Run Gemma 3 4B IT?
Q4_K_M · 2.8 GBGemma 3 4B IT (Q4_K_M) requires 2.8 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 4+ 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 3 4B IT, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 3.0 GB free · up to 32K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~174Simulate output on RTX 3080RTX 2080 Ti~141Simulate output on RTX 2080 TiRTX 3070 Ti~139Simulate output on RTX 3070 TiM3*8 GB~25Simulate output on iMac 24" M3 (8 GB)Orin Nano~23Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~17Simulate output on iPhone 1720 GB
fits · 15.0 GB free · up to 32K ctx
1 GPU
RX 7900 XT~169Simulate output on RX 7900 XT32–40 GB
fits · 27.0 GB free · up to 32K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~410Simulate output on RTX 5090M5 Max36 GB~113Simulate output on Mac Studio M5 Max (36 GB)M532 GB~38Simulate output on MacBook Air 13" M5 (32 GB)Orin~47Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~31Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
How good is Gemma 3 4B IT?
The llmrun Score merges 5 public benchmark boards into a single figure, where 100 represents the average for open models.
Score vs VRAM in the 24 GB tier
- Gemma 3 4B IT
- Other models
- Best Score for its VRAM
#33 of 35 that fit 24 GB
Each dot is a model at the best quant that fits a 24 GB GPU. The line joins the models with the best Score for their 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 · Mar 2025Independent
Independent23.2%
#93/98 open
- LMArena Text
LMArena · Oct 2026Arena
Arena1303.3
#105/187 open
- AIME 2024/2025
Epoch AI · Mar 2025Independent
Independent7.5%
#64/86 open
- MMLU-Pro
TIGER-LabIndependent
Independent43.6%
#92/145 open
- DTBench
Epoch AI · Mar 2025Lab-reported
Lab-reported50.9%
#58/68 open
- LMCA
Epoch AI · Mar 2025Lab-reported
Lab-reported2.8%
#54/54 open
In the 24 GB class
35 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
122.1
~38 tok/s · 17.9 GB
- #2
Qwen3.6 27BAlibaba
111.2
~38 tok/s · 17.9 GB
- #3
Gemma 4 31B ITGoogle
106.8
~32 tok/s · 21.7 GB
- #4
Qwen3.6 35B A3BAlibaba
106.8
~151 tok/s · 22.0 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 3 4B IT
Gemma 3 family · 20 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
Qwen2.5 7B Instruct
Alibaba
- 1.1 higher Score
- 0.8 GB more VRAM
- 99 tok/s slower
Score 65.1 · 5.8 GB · ~131 tok/s
Other vendor
Qwen3.5 9B
Alibaba
- 35.4 higher Score
- 1.6 GB more VRAM
- 128 tok/s slower
Score 99.4 · 6.6 GB · ~103 tok/s
Similar models
10| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Qwen3 8BAlibaba | 93.9 | 7.6 GB | ~119 | similar score |
| Gemma 2 9B ITGoogle | 68.0 | 7.3 GB | ~107 | similar score |
| Llama 3.1 8B InstructMeta | 62.5 | 7.9 GB | ~124 | similar score |
| Meta Llama 3 8B InstructMeta | 61.7 | 7.9 GB | ~124 | similar score |
| Granite Vision 4.1 4BIBM | — | 4 GB | ~228 | same size |
| Qwen3 VL 4B InstructAlibaba | — | 4.5 GB | ~208 | same size |
| MiniCPM V 4OpenBMB | — | 3.1 GB | ~236 | same size |
| Phi 3.5 Vision InstructMicrosoft | — | 9.2 GB | ~183 | same size |
| Nanbeige4.2 3BNanbeige | — | 3.5 GB | ~227 | same size |
| Agents A1 4BInternScience | — | 3.4 GB | ~205 | same size |
Specifications
- Publisher
- Family
- Gemma 3
- Parameters
- 4.3B
- Release Date
- 2025-02-20
- License
- Gemma Terms
Frequently Asked Questions
How much VRAM does Gemma 3 4B IT need?
Gemma 3 4B IT requires 2.8 GB of VRAM at Q4_K_M, or 9.5 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 4.3B × 4.8 bits ÷ 8 = 2.6 GB
KV Cache + Overhead ≈ 0.2 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 3 4B IT?
For Gemma 3 4B IT, Q4_K_M (2.8 GB) offers the best balance of quality and VRAM usage. Q4_K_L (2.9 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 1.3 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Gemma 3 4B IT on a Mac?
Yes — Mac Mini M2 (8 GB) and 145 other Macs can run Gemma 3 4B IT. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 2.8 GB of usable unified memory (RAM minus macOS overhead).
Can I run Gemma 3 4B IT locally?
Yes — Gemma 3 4B IT can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Gemma 3 4B IT?
At Q4_K_M, Gemma 3 4B IT can reach ~1690 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~231 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 ÷ 2.84 × 0.65 = ~1831 tok/s
Estimated speed at Q4_K_M (2.8 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Gemma 3 4B IT?
At Q4_K_M, the download is about 2.58 GB. The full-precision BF16 version is 8.60 GB. The smallest option (IQ2_XXS) is 1.18 GB.
Which GPUs can run Gemma 3 4B IT?
52 consumer GPUs can run Gemma 3 4B IT 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 3 4B IT?
163 devices with unified memory can run Gemma 3 4B IT at Q4_K_M (2.8 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.