Open-weight model
temp-llada-instruct-30-snr-weighted
by Shruthi Muthukumar BashCache/temp-llada-instruct-30-snr-weighted
temp-llada-instruct-30-snr-weighted is an open-weight model from Shruthi Muthukumar. It has 6.2B parameters. At 16-bit it needs about 14.9 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 temp-llada-instruct-30-snr-weighted (6.2B 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 | 12.4 GB | 14.9 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 6.2 GB | 7.5 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 3.1 GB | 3.7 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.
temp-llada-instruct-30-snr-weighted on every accelerator the SAVRN Index prices, at every precision
Model Card
The publisher has not written a card for this model.
Configuration
- Architecture
- LLaDAModelLM
- Vocabulary size
- 126,464
- RoPE base
- 500000
- Stored precision
- bfloat16
- Model type
- llada
Identity and Version
- Repository
- BashCache/temp-llada-instruct-30-snr-weighted
- Publisher
- Shruthi Muthukumar
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 6.2B parameters
- Languages
- Not stated by the source
- Revision
- 74e1dba40adbf2115a2de531f3ed9686b3c3dc78
- First published
- 2026-10-08
- Last updated
- 2026-10-08
Files and Weights
7 files, 12.4 GB in total. The weights are 1 file totalling 12.4 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 12.4 GB | b213aa6acb35 |
| config.json | Configuration | 2.1 KB | — |
| generation_config.json | Configuration | 121 B | — |
| special_tokens_map.json | Configuration | 779 B | — |
| .gitattributes | Repository | 1.5 KB | — |
| tokenizer.json | Tokenizer | 9.7 MB | — |
| tokenizer_config.json | Tokenizer | 51.7 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 12.4 GB
Released by Shruthi Muthukumar through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 12.4 GB |
| 16-bit | 12.4 GB |
| 8-bit | 6.2 GB |
| 4-bit | 3.1 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About temp-llada-instruct-30-snr-weighted
How much GPU memory does temp-llada-instruct-30-snr-weighted need?
About 14.9 GB at 16-bit and 3.7 GB at 4-bit: the weights (6.2B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run temp-llada-instruct-30-snr-weighted 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.