Open-weight model
opus-4.8-recreation-1b-light
by CyberviserAI GLASSEYE/opus-4.8-recreation-1b-light
Latest local refresh: see opus-4.8-recreation-1b-light-v4 under the same org (glasseye RTX 5070).
Runs On
What it takes to serve opus-4.8-recreation-1b-light (929M 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 | 1.9 GB | 2.2 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.9 GB | 1.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.5 GB | 0.6 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
By CyberviserAI, published under mit, revision 11c950b9a350.
Latest local refresh: see opus-4.8-recreation-1b-light-v4 under the same org (glasseye RTX 5070).
Read CyberviserAI's full model card
Opus 1B Light (baseline)
Latest local refresh: see opus-4.8-recreation-1b-light-v4 under the same org (glasseye RTX 5070).
Configuration
- Vocabulary size
- 199,998
- RoPE base
- 500000
Identity and Version
- Repository
- GLASSEYE/opus-4.8-recreation-1b-light
- Publisher
- CyberviserAI
- Task
- Not stated by the source
- Modality
- Other
- Library
- open_mythos
- Parameters
- 929M parameters
- Languages
- Not stated by the source
- Revision
- 11c950b9a350bfddf88f8fd81227709ce04ef8b7
- First published
- 2026-05-31
- Last updated
- 2026-09-18
Files and Weights
6 files, 5.8 GB in total. The weights are 2 files totalling 5.8 GB in bin, safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 3.7 GB | 9c8dce601172 |
| pytorch_model.bin | Weights | 2.1 GB | 809179af07b3 |
| build_metadata.json | Configuration | 589 B | — |
| config.json | Configuration | 538 B | — |
| README.md | Documentation | 180 B | — |
| .gitattributes | Repository | 1.6 KB | — |
License and Download
- License
- mit
- Access
- Open weights, no gate
- Download size
- 5.8 GB
Released by CyberviserAI through its official repository on Hugging Face. Read the license.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 5.8 GB |
| 16-bit | 1.9 GB |
| 8-bit | 0.9 GB |
| 4-bit | 0.5 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About opus-4.8-recreation-1b-light
How much GPU memory does opus-4.8-recreation-1b-light need?
About 2.2 GB at 16-bit and 0.6 GB at 4-bit: the weights (929M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run opus-4.8-recreation-1b-light 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 opus-4.8-recreation-1b-light commercially?
Yes. opus-4.8-recreation-1b-light 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.