Cloreva-X1-2.1B is an open-weight model from Muhammad Alwi. It has 2.4B parameters and a 120,000-token context. At 16-bit it needs about 5.7 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 Cloreva-X1-2.1B (2.4B 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 | 4.7 GB | 5.7 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 2.4 GB | 2.8 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 1.2 GB | 1.4 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.
Cloreva-X1-2.1B on every accelerator the SAVRN Index prices, at every precision
Model Card
The publisher has not written a card for this model.
Configuration
- Context length (tokens)
- 120,000
- Layers
- 30
- Hidden size
- 1,632
- Feed-forward size
- 9,280
- Key/value heads
- 2
- Head dimension
- 136
- Vocabulary size
- 155,072
- Sliding window (tokens)
- 120,000
- RoPE base
- 1e+06
- Model type
- resonet
Identity and Version
- Repository
- Zulkiflii/Cloreva-X1-2.1B
- Publisher
- Muhammad Alwi
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 2.4B parameters
- Languages
- Not stated by the source
- Revision
- dc7e36001d5e97da435088cc65ee0a2acf865481
- First published
- 2026-09-28
- Last updated
- 2026-09-29
Files and Weights
12 files, 4.7 GB in total. The weights are 1 file totalling 4.7 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 4.7 GB | efc4d8b51756 |
| added_tokens.json | Configuration | 682 B | — |
| config.json | Configuration | 1.2 KB | — |
| configuration_resonet.py | Configuration | 7.7 KB | — |
| flash_kuramoto.py | Configuration | 20.9 KB | — |
| modeling_resonet.py | Configuration | 43.0 KB | — |
| chat_template.jinja | Other | 2.5 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| merges.txt | Tokenizer | 1.7 MB | — |
| tokenizer.json | Tokenizer | 12.8 MB | c00973e806bd |
| tokenizer_config.json | Tokenizer | 783 B | — |
| vocab.json | Tokenizer | 2.8 MB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 4.7 GB
Released by Muhammad Alwi through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 4.7 GB |
| 16-bit | 4.7 GB |
| 8-bit | 2.4 GB |
| 4-bit | 1.2 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About Cloreva-X1-2.1B
How much GPU memory does Cloreva-X1-2.1B need?
About 5.7 GB at 16-bit and 1.4 GB at 4-bit: the weights (2.4B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run Cloreva-X1-2.1B 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 Cloreva-X1-2.1B's context length?
120,000 tokens, from the maximum position embeddings in its published configuration.