Open-weight model
gemma-4-e4b-kinetics417K_FFT
by THChou1220 THChou1220/gemma-4-e4b-kinetics417K_FFT
gemma-4-e4b-kinetics417K_FFT is an open-weight model from THChou1220, released under Apache License 2.0. It has 8B parameters and a 131,072-token context. At 16-bit it needs about 19.2 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
Runs On
What it takes to serve gemma-4-e4b-kinetics417K_FFT (8B 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 | 16.0 GB | 19.2 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 8.0 GB | 9.6 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 4.0 GB | 4.8 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 Oct 18, 2026.
gemma-4-e4b-kinetics417K_FFT on every accelerator the SAVRN Index prices, at every precision
Model Card
The publisher has not written a card for this model.
Configuration
- Architecture
- Gemma4ForConditionalGeneration
- Context length (tokens)
- 131,072
- Layers
- 42
- Hidden size
- 2,560
- Feed-forward size
- 10,240
- Attention heads
- 8
- Key/value heads
- 2
- Head dimension
- 256
- Vocabulary size
- 262,144
- Sliding window (tokens)
- 512
- Model type
- gemma4
Identity and Version
- Repository
- THChou1220/gemma-4-e4b-kinetics417K_FFT
- Publisher
- THChou1220
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 8B parameters
- Languages
- Not stated by the source
- Revision
- 4140a23c26110aeca334a3cfaad1f1636c98d386
- First published
- 2026-10-09
- Last updated
- 2026-10-09
Files and Weights
10 files, 16.0 GB in total. The weights are 1 file totalling 16.0 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 16.0 GB | 109c2c36f3be |
| config.json | Configuration | 5.3 KB | — |
| generation_config.json | Configuration | 211 B | — |
| processor_config.json | Configuration | 1.7 KB | — |
| trainer_state.json | Configuration | 18.6 KB | — |
| README.md | Documentation | 28 B | — |
| chat_template.jinja | Other | 18.6 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer.json | Tokenizer | 32.2 MB | cc8d3a0ce364 |
| tokenizer_config.json | Tokenizer | 2.7 KB | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 16.0 GB
Released by THChou1220 through its official repository on Hugging Face. Read the license.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 16.0 GB |
| 16-bit | 16.0 GB |
| 8-bit | 8.0 GB |
| 4-bit | 4.0 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About gemma-4-e4b-kinetics417K_FFT
How much GPU memory does gemma-4-e4b-kinetics417K_FFT need?
About 19.2 GB at 16-bit and 4.8 GB at 4-bit: the weights (8B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run gemma-4-e4b-kinetics417K_FFT 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.
Can I use gemma-4-e4b-kinetics417K_FFT commercially?
Yes. gemma-4-e4b-kinetics417K_FFT is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.
What is gemma-4-e4b-kinetics417K_FFT's context length?
131,072 tokens, from the maximum position embeddings in its published configuration.