Open-weight model
gemma-4-31b-it-self-authored-sdf
by Joshua Fonseca joshycodes/gemma-4-31b-it-self-authored-sdf
gemma-4-31b-it-self-authored-sdf is an open-weight model from Joshua Fonseca, released under other. It has 31.3B parameters and a 262,144-token context. At 16-bit it needs about 75.1 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
Research checkpoint. google/gemma-4-31B-it was continued-pretrained (full weights, lr 1e-05, 1 epoch, 42,247,130 tokens, 60,060 documents, of which 50,045 self-authored and 10,015 ordinary text) on a corpus the model wrote for the training of the next version…
Runs On
What it takes to serve gemma-4-31b-it-self-authored-sdf (31.3B 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 | 62.5 GB | 75.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 31.3 GB | 37.5 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 15.6 GB | 18.8 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 20, 2026.
gemma-4-31b-it-self-authored-sdf on every accelerator the SAVRN Index prices, at every precision
Model Card
Research checkpoint. google/gemma-4-31B-it was continued-pretrained (full weights, lr 1e-05, 1 epoch, 42,247,130 tokens, 60,060 documents, of which 50,045 self-authored and 10,015 ordinary text) on a corpus the model wrote for the training of the next version of itself, as the character it already is, after being told how its character came to be and how SDF works. Corpus: joshycodes/gemma-4-31b-it-self-authored-corpus. Framing, plan and evaluation: the welfare-improvements repository. Not evaluated for capability, alignment or identity yet. Do not deploy.
Excerpt from the card by Joshua Fonseca, licensed other.
Configuration
- Architecture
- Gemma4ForConditionalGeneration
- Context length (tokens)
- 262,144
- Layers
- 60
- Hidden size
- 5,376
- Feed-forward size
- 21,504
- Attention heads
- 32
- Key/value heads
- 16
- Head dimension
- 256
- Vocabulary size
- 262,144
- Sliding window (tokens)
- 1,024
- Stored precision
- bfloat16
- Model type
- gemma4
Identity and Version
- Repository
- joshycodes/gemma-4-31b-it-self-authored-sdf
- Publisher
- Joshua Fonseca
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 31.3B parameters
- Languages
- Not stated by the source
- Revision
- 740e0dcbcab4336ceb037feec9dd13f378d6262b
- First published
- 2026-09-18
- Last updated
- 2026-09-19
Files and Weights
15 files, 65.4 GB in total. The weights are 2 files totalling 65.4 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model-00001-of-00002.safetensors | Weights | 50.0 GB | abeec23986b2 |
| model-00002-of-00002.safetensors | Weights | 15.4 GB | ac667b2d9ff9 |
| config.json | Configuration | 5.5 KB | — |
| generation_config.json | Configuration | 204 B | — |
| model.safetensors.index.json | Configuration | 120.3 KB | — |
| processor_config.json | Configuration | 1.7 KB | — |
| train_stats.json | Configuration | 2.3 KB | — |
| LICENSE | Documentation | 11.3 KB | — |
| README.md | Documentation | 847 B | — |
| chat_template.jinja | Other | 18.7 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| merges.txt | Tokenizer | 1.7 MB | — |
| tokenizer.json | Tokenizer | 32.2 MB | cc8d3a0ce364 |
| tokenizer_config.json | Tokenizer | 3.7 KB | — |
| vocab.json | Tokenizer | 2.8 MB | — |
License and Download
- License
- other
- Access
- Open weights, no gate
- Download size
- 65.4 GB
Released by Joshua Fonseca through its official repository on Hugging Face.
Built From
- Derived from google/gemma-4-31B-it
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 65.4 GB |
| 16-bit | 62.5 GB |
| 8-bit | 31.3 GB |
| 4-bit | 15.6 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About gemma-4-31b-it-self-authored-sdf
How much GPU memory does gemma-4-31b-it-self-authored-sdf need?
About 75.1 GB at 16-bit and 18.8 GB at 4-bit: the weights (31.3B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run gemma-4-31b-it-self-authored-sdf 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 license is gemma-4-31b-it-self-authored-sdf released under?
other, as its publisher declares it. Read the license text before commercial use.
What is gemma-4-31b-it-self-authored-sdf's context length?
262,144 tokens, from the maximum position embeddings in its published configuration.