Open-weight model
gemma4-internal-meta-location-fp8
by Le Phat Minh lephatminh/gemma4-internal-meta-location-fp8
gemma4-internal-meta-location-fp8 is an open-weight model from Le Phat Minh, released under MIT License. It has 7.9B parameters and a 131,072-token context. At 16-bit it needs about 19.1 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 gemma4-internal-meta-location-fp8 (7.9B 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 | 15.9 GB | 19.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 7.9 GB | 9.5 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.
gemma4-internal-meta-location-fp8 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
- Stored precision
- bfloat16
- Model type
- gemma4
- Quantization
- compressed-tensors
Identity and Version
- Repository
- lephatminh/gemma4-internal-meta-location-fp8
- Publisher
- Le Phat Minh
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 7.9B parameters
- Languages
- Not stated by the source
- Revision
- 607a30b535d602b956c009586497cba3bfba4727
- First published
- 2026-10-09
- Last updated
- 2026-10-09
Files and Weights
10 files, 11.5 GB in total. The weights are 1 file totalling 11.5 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 11.5 GB | 3c8763e9ece6 |
| config.json | Configuration | 6.6 KB | — |
| generation_config.json | Configuration | 204 B | — |
| processor_config.json | Configuration | 1.7 KB | — |
| recipe.yaml | Configuration | 215 B | — |
| README.md | Documentation | 21 B | — |
| chat_template.jinja | Other | 18.6 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer.json | Tokenizer | 32.2 MB | cc8d3a0ce364 |
| tokenizer_config.json | Tokenizer | 3.7 KB | — |
License and Download
- License
- mit
- Access
- Open weights, no gate
- Download size
- 11.5 GB
Released by Le Phat Minh through its official repository on Hugging Face. Read the license.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 11.5 GB |
| 16-bit | 15.9 GB |
| 8-bit | 7.9 GB |
| 4-bit | 4.0 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About gemma4-internal-meta-location-fp8
How much GPU memory does gemma4-internal-meta-location-fp8 need?
About 19.1 GB at 16-bit and 4.8 GB at 4-bit: the weights (7.9B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run gemma4-internal-meta-location-fp8 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 gemma4-internal-meta-location-fp8 commercially?
Yes. gemma4-internal-meta-location-fp8 is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included.
What is gemma4-internal-meta-location-fp8's context length?
131,072 tokens, from the maximum position embeddings in its published configuration.