// Gemma · Text LLM
gemma-2-27b-it: VRAM & local deployment
27.2B parameters. About 18.7 GB at 4-bit and 60.4 GB at BF16.
released 2024-06-24licence: Commercial with conditionsmemory figures are estimates
01Specs
| Publisher | Google · google |
|---|---|
| Family / series | Gemma · gemma-2 |
| Type | Text LLM (text-generation) |
| Parameters | 27.2B Source: counted from official safetensors weights |
| Context length | — |
| Released weights | BF16 · 54.5 GBdownload |
| Licence | Gemma Terms of Use · Commercial with conditionsCommercial use allowed under the publisher’s own licence terms (user caps, acceptable-use policy, attribution or region limits). Read it before shipping. |
| Released | 2024-06-24 (Hugging Face repo created) |
| Access | Gated: accept the licence on Hugging Face before downloading. |
02How much VRAM it needs (estimate)
Total = weights + 10% + 0.5GB overhead + KV cache for one request (FP16 KV). More concurrent users multiply the KV column.
| Precision | Weights | Smallest GPU | Mac |
|---|---|---|---|
| BF16 / FP16 (original) | 54.5 GB | H100 80GB | Mac 128GB |
| FP8 / INT8 / Q8_0 | 28.9 GB | 2 × RTX 5090 (64GB) | Mac 64GB |
| 4-bit (Q4_K_M / AWQ / GPTQ-Int4) | 16.5 GB | RTX 4090 24GB | Mac 36GB |
KV cache not estimated: the official config.json is gated or lacks attention parameters. Totals above are weights + overhead only.
Bits per weight: BF16 16, FP8 8.5, 4-bit 4.85. “Fits” = total ≤ 90% of memory; Mac GPU can use ~2/3 of unified memory (≤36GB) or ~3/4 (larger). For MoE, all experts must be in memory, so size by total parameters. Method →
03How to run it
Only runtimes the publisher or the runtime’s official library names for this model.
- Transformers — mentioned in the official model card
- Ollama — in the official Ollama library · gemma2:27b
ollama run gemma2:27b04Official repositories & quantised builds
2 official repo(s) from google.
- gemma-2-27b-it Instruct
- gemma-2-27b main
05Other Gemma models
All 48 →| Model | Params | 4-bit total | Released |
|---|---|---|---|
| gemma-2-2b-it · same series | 2.61B | 2.2 GB | 2024-07-16 |
| gemma-2-9b-it · same series | 9.24B | 6.7 GB | 2024-06-24 |
| embeddinggemma-2 | 744M | 1.0 GB | 2026-09-14 |
| diffusiongemma-26B-A4B-it | 25.8B / 4B | 18.3 GB | 2026-06-09 |
| gemma-4-12B-it-qat-q4_0-unquantized | 12B | 9.3 GB | 2026-06-04 |
| gemma-4-12B-it | 12B | 9.3 GB | 2026-05-23 |
| gemma-4-E4B-it-qat-q4_0-unquantized | 7.94B | 5.9 GB | 2026-04-30 |
| gemma-4-E2B-it-qat-q4_0-unquantized | 5.1B | 4.0 GB | 2026-04-29 |
| gemma-4-26B-A4B-it-qat-q4_0-unquantized | 25.8B / 4B | 18.3 GB | 2026-04-29 |
| gemma-4-31B-it-qat-q4_0-unquantized | 31.3B | 23.5 GB | 2026-04-28 |
06Sources
Data checked 2024-08-27. Parameters, context and licence are copied from the official repository; memory figures are our estimates.