Open-weight model
d24-v62-unified-const05pct-audited-step12070
by Yuda Song sfanm/d24-v62-unified-const05pct-audited-step12070
Runs On
What it takes to serve d24-v62-unified-const05pct-audited-step12070 (757M 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 | 1.5 GB | 1.8 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.8 GB | 0.9 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.4 GB | 0.5 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
- LlamaForCausalLM
- Context length (tokens)
- 2,048
- Layers
- 24
- Hidden size
- 1,536
- Feed-forward size
- 4,096
- Attention heads
- 12
- Key/value heads
- 12
- Head dimension
- 128
- Vocabulary size
- 50,304
- Model type
- llama
Identity and Version
- Repository
- sfanm/d24-v62-unified-const05pct-audited-step12070
- Publisher
- Yuda Song
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 757M parameters
- Languages
- Not stated by the source
- Revision
- 9189d3029d9f855d28108dd74e81b39d31c2e305
- First published
- 2026-09-18
- Last updated
- 2026-09-18
Files and Weights
8 files, 3.0 GB in total. The weights are 1 file totalling 3.0 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 3.0 GB | db9687b41bc8 |
| config.json | Configuration | 733 B | — |
| generation_config.json | Configuration | 202 B | — |
| milestone.json | Configuration | 355 B | — |
| chat_template.jinja | Other | 197 B | — |
| .gitattributes | Repository | 1.5 KB | — |
| tokenizer.json | Tokenizer | 3.6 MB | — |
| tokenizer_config.json | Tokenizer | 349 B | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 3.0 GB
Released by Yuda Song through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 3.0 GB |
| 16-bit | 1.5 GB |
| 8-bit | 0.8 GB |
| 4-bit | 0.4 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About d24-v62-unified-const05pct-audited-step12070
How much GPU memory does d24-v62-unified-const05pct-audited-step12070 need?
About 1.8 GB at 16-bit and 0.5 GB at 4-bit: the weights (757M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run d24-v62-unified-const05pct-audited-step12070 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 d24-v62-unified-const05pct-audited-step12070's context length?
2,048 tokens, from the maximum position embeddings in its published configuration.