Runs On
What it takes to serve gemma-4-12b-it-r64-t2g-sft (12B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 23.9 GB | 28.7 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 12.0 GB | 14.4 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 6.0 GB | 7.2 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Sep 18, 2026.
Model Card
The publisher has not written a card for this model.
Configuration
- Architecture
- Gemma4UnifiedForConditionalGeneration
- Context length (tokens)
- 262,144
- Layers
- 48
- Hidden size
- 3,840
- Feed-forward size
- 15,360
- Attention heads
- 16
- Key/value heads
- 8
- Head dimension
- 256
- Vocabulary size
- 262,144
- Sliding window (tokens)
- 1,024
- Stored precision
- bfloat16
- Model type
- gemma4_unified
Identity and Version
- Repository
- lettria-rd/gemma-4-12b-it-r64-t2g-sft
- Publisher
- Lettria R&D
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 12B parameters
- Languages
- Not stated by the source
- Revision
- f079ee0f089c4a1754a68994ebe260fc86a48949
- First published
- 2026-09-18
- Last updated
- 2026-09-18
Files and Weights
8 files, 24.0 GB in total. The weights are 1 file totalling 23.9 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 23.9 GB | 9c8cf70be08e |
| config.json | Configuration | 5.9 KB | — |
| generation_config.json | Configuration | 255 B | — |
| processor_config.json | Configuration | 1.4 KB | — |
| chat_template.jinja | Other | 638 B | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer.json | Tokenizer | 32.2 MB | 984a48a60a63 |
| tokenizer_config.json | Tokenizer | 6.0 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 23.9 GB
Released by Lettria R&D through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 23.9 GB |
| 16-bit | 23.9 GB |
| 8-bit | 12.0 GB |
| 4-bit | 6.0 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About gemma-4-12b-it-r64-t2g-sft
How much GPU memory does gemma-4-12b-it-r64-t2g-sft need?
About 28.7 GB at 16-bit and 7.2 GB at 4-bit: the weights (12B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run gemma-4-12b-it-r64-t2g-sft on?
At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
What is gemma-4-12b-it-r64-t2g-sft's context length?
262,144 tokens, from the maximum position embeddings in its published configuration.