Gemma 3 270M IT Qat Q4 0 Unquantized — Hardware Requirements & GPU Compatibility
Chat
Gemma 3 270M IT Qat Q4 0 Unquantized is a 268M-parameter open language model from Google in the Gemma 3 family. At Q4_K_M it needs about 0.18 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 · ~3640 tok/s · 32K)Macs from 8 GB (Q4_K_M · ~398 tok/s)
Gemma Terms
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Gemma 3 270M IT Qat Q4 0 Unquantized
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 hf.co/unsloth/gemma-3-270m-it-qat-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 22.8 GB free · 16K context
Download: gemma-3-270m-it-qat-Q4_K_M.gguf0.25 GBunsloth
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 3080 Ti (12 GB) (10 GB headroom) · Q4_K_M
- Generation speed
- ~3295 tok/s
- generation speed
- Cost per 1M output tokens
- $0.010
- per 1M output tokens
How Much VRAM Does Gemma 3 270M IT Qat Q4 0 Unquantized Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 0.1 GB | 2.3 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 32K context · ~5040 tok/s | |
| 0.1 GB | 2.3 GB | 3-bit small — 3-bit small quantization | Fits: 32K context · ~5040 tok/s | |
| 0.1 GB | 2.3 GB | 3-bit medium — 3-bit medium quantization | Fits: 32K context · ~4680 tok/s | |
| 0.1 GB | 2.3 GB | 4-bit · legacy — 4-bit legacy quantization | Fits: 32K context · ~4368 tok/s | |
| 0.2 GB | 2.3 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 32K context · ~3640 tok/s | |
| 0.2 GB | 2.3 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 32K context · ~3120 tok/s | |
| 0.2 GB | 2.4 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 32K context · ~2730 tok/s | |
| 0.3 GB | 2.4 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 32K context · ~2259 tok/s |
Selected Q4_K_M
4-bit medium quantization1.2GBat 16K context
- Weights
- 0.1 GB
- KV cache
- 0.8 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 22.8 GB free · ~3640 tok/s
≥50 tok/s needs ≥14 GB/s · RTX 5090 ~6471, RTX 3090 Ti ~3640
Which Hardware Can Run Gemma 3 270M IT Qat Q4 0 Unquantized?
Q4_K_M · 0.2 GBGemma 3 270M IT Qat Q4 0 Unquantized (Q4_K_M) requires 0.2 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 1+ 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 270M IT Qat Q4 0 Unquantized, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 6.8 GB free · up to 32K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~2746Simulate output on RTX 3080RTX 2080 Ti~2224Simulate output on RTX 2080 TiRTX 3070 Ti~2197Simulate output on RTX 3070 TiM3*8 GB~398Simulate output on iMac 24" M3 (8 GB)Orin Nano~368Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~265Simulate output on iPhone 1720 GB
fits · 18.8 GB free · up to 32K ctx
1 GPU
RX 7900 XT~2667Simulate output on RX 7900 XT32–40 GB
fits · 30.8 GB free · up to 32K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~6471Simulate output on RTX 5090M5 Max36 GB~1789Simulate output on Mac Studio M5 Max (36 GB)M532 GB~597Simulate output on MacBook Air 13" M5 (32 GB)Orin~740Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~488Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to Gemma 3 270M IT Qat Q4 0 Unquantized
Gemma 3 family · 20 models →Similar models
4| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| SmolVLM2 256M Video InstructHugging Face | — | 0.6 GB | ~1310 | same size |
| SmolVLM 256M InstructHugging Face | — | 0.6 GB | ~1310 | same size |
| Vlt5 Base KeywordsVoicelab | — | 1.6 GB | ~1074 | same size |
| Functiongemma 270M ITGoogle | — | 1.6 GB | ~1111 | same size |
Specifications
- Publisher
- Family
- Gemma 3
- Parameters
- 268M
- Release Date
- 2025-08-07
- License
- Gemma Terms
Frequently Asked Questions
How much VRAM does Gemma 3 270M IT Qat Q4 0 Unquantized need?
Gemma 3 270M IT Qat Q4 0 Unquantized requires 0.2 GB of VRAM at Q4_K_M, or 0.6 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 268M × 4.8 bits ÷ 8 = 0.2 GB
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 270M IT Qat Q4 0 Unquantized?
For Gemma 3 270M IT Qat Q4 0 Unquantized, Q4_K_M (0.2 GB) offers the best balance of quality and VRAM usage. Q4_K_L (0.2 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 0.1 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Gemma 3 270M IT Qat Q4 0 Unquantized on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run Gemma 3 270M IT Qat Q4 0 Unquantized. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 0.2 GB of usable unified memory (RAM minus macOS overhead).
Can I run Gemma 3 270M IT Qat Q4 0 Unquantized locally?
Yes — Gemma 3 270M IT Qat Q4 0 Unquantized can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Gemma 3 270M IT Qat Q4 0 Unquantized?
At Q4_K_M, Gemma 3 270M IT Qat Q4 0 Unquantized can reach ~26667 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~3640 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 ÷ 0.18 × 0.65 = ~28889 tok/s
Estimated speed at Q4_K_M (0.2 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 270M IT Qat Q4 0 Unquantized?
At Q4_K_M, the download is about 0.16 GB. The full-precision BF16 version is 0.54 GB. The smallest option (IQ2_XXS) is 0.07 GB.
Which GPUs can run Gemma 3 270M IT Qat Q4 0 Unquantized?
52 consumer GPUs can run Gemma 3 270M IT Qat Q4 0 Unquantized 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 270M IT Qat Q4 0 Unquantized?
163 devices with unified memory can run Gemma 3 270M IT Qat Q4 0 Unquantized at Q4_K_M (0.2 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.