Unsloth
gemma 3 27b it (27B parameters) requires approximately 21.4 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 25 GB of VRAM.
Quick specs
Related models
Inference speed
Estimated decode speed (tokens/sec) for gemma 3 27b it at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~73 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.
| GPU / Mac | Memory | Quant | Speed (tok/s) | Fits? |
|---|---|---|---|---|
 RTX 5090 32GB | 32 GB | Q4_K_M | 72.9 | Fits |
| RTX 4090 24GB | 24 GB | Q4_K_M | 46.5 | Offloads |
Quick picks
Best hardware
Run this model
Quantization
How much VRAM gemma 3 27b it (27B) needs at each GGUF quant, and whether it fits a 24 GB card (RTX 4090 / 3090). The recommended Q4_K_M uses ~16.5 GB — about 43% less VRAM than Q8_0, at a small quality cost.
| Quant | Bits | VRAM (weights) | Quality | Fits 24 GB? |
|---|---|---|---|---|
| Q2_K | 2 | 10.5 GB | Low | Fits |
| Q3_K_S | 3 | 13.2 GB | Low | Tight |
| NVFP4 | 4 | 15.1 GB | Medium | Tight |
| Q4_K_Mrecommended | 4 | 16.5 GB | Medium | Offloads |
Hardware compatibility
Computing compatibility...
Memory breakdown
Frequently asked questions
gemma 3 27b it (27B parameters) requires approximately 21.4 GB of VRAM with Q4_K_M quantization. Lower quantizations like Q4_K_M use less memory but may reduce quality.
Yes, Mac mini M4 64GB can run gemma 3 27b it with a compatibility score of 47/100. It provides 64 GB of memory and achieves approximately 8.7 tokens per second.
The recommended quantization for gemma 3 27b it is Q4_K_M, which offers the best balance between model quality and memory efficiency. Higher quantizations preserve more quality but require more VRAM.
The top recommended hardware for gemma 3 27b it: RTX 5090 32GB (score: 56/100), AMD Instinct MI100 32GB (score: 55/100), NVIDIA A100 40GB (score: 55/100). These provide the best combination of memory, bandwidth, and compute for running this model locally.
Yes, gemma 3 27b it is well-suited for chat. It was designed with these use cases in mind.
See also
| 24 GB |
| Q4_K_M |
| 42.0 |
| Offloads |
| RTX 3090 24GB | 24 GB | Q4_K_M | 39.8 | Offloads |
Mac Studio M3 Ultra 256GB | 256 GB | Q4_K_M | 33.8 | Fits |
MacBook Pro M4 Max 128GB | 128 GB | Q4_K_M | 33.4 | Fits |
MacBook Pro M4 Max 64GB | 64 GB | Q4_K_M | 33.4 | Fits |
Mac Studio M2 Ultra 128GB | 128 GB | Q4_K_M | 28.2 | Fits |
Mac Studio M1 Ultra 128GB | 128 GB | Q4_K_M | 26.7 | Fits |
MacBook Pro M4 Pro 48GB | 48 GB | Q4_K_M | 21.1 | Fits |
MacBook Pro M3 Max 64GB | 64 GB | Q4_K_M | 14.6 | Fits |
| RTX 4080 Super 16GB | 16 GB | Q4_K_M | 13.7 | Too big |
MacBook Pro M1 Max 64GB | 64 GB | Q4_K_M | 13.4 | Fits |
| RTX 4070 12GB | 12 GB | Q4_K_M | 4.8 | Too big |
| RTX 3060 12GB | 12 GB | Q4_K_M | 3.0 | Too big |
| RTX 4060 8GB | 8 GB | Q4_K_M | 2.0 | Too big |
Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.
| Q5_K_M |
| 5 |
| 19.4 GB |
| High |
| Offloads |
| Q6_K | 6 | 22.1 GB | High | Heavy offload |
| Q8_0 | 8 | 28.9 GB | Very High | Too big |
| F16 | 16 | 55.4 GB | Maximum | Too big |
VRAM shown is quantized weights only; add ~1–3 GB runtime overhead plus KV cache for your context length. Lower quants trade quality for memory — Q4_K_M is the usual sweet spot; Q2/Q3 only when you must fit a bigger model.
