andromeda-gguf is an open-weight model from Enderman98. It has 12.2B parameters and a 131,072-token context. At 16-bit it needs about 29.4 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 andromeda-gguf (12.2B 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 | 24.5 GB | 29.4 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 12.2 GB | 14.7 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 6.1 GB | 7.3 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.
andromeda-gguf on every accelerator the SAVRN Index prices, at every precision
Model Card
The publisher has not written a card for this model.
Configuration
- Architecture
- MistralForCausalLM
- Context length (tokens)
- 131,072
- Layers
- 40
- Hidden size
- 5,120
- Feed-forward size
- 14,336
- Attention heads
- 32
- Key/value heads
- 8
- Head dimension
- 128
- Vocabulary size
- 131,072
- Stored precision
- bfloat16
- Model type
- mistral
Identity and Version
- Repository
- Ender98/andromeda-gguf
- Publisher
- Enderman98
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 12.2B parameters
- Languages
- Not stated by the source
- Revision
- 0632d5ea092cae33e171fa8b8c4fef63f17b713e
- First published
- 2026-09-29
- Last updated
- 2026-09-29
Files and Weights
12 files, 24.5 GB in total. The weights are 5 files totalling 24.5 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model-00001-of-00005.safetensors | Weights | 4.9 GB | 297f9ce53bd4 |
| model-00002-of-00005.safetensors | Weights | 4.9 GB | 561393ba0916 |
| model-00003-of-00005.safetensors | Weights | 4.9 GB | 9f8e726abfb1 |
| model-00004-of-00005.safetensors | Weights | 4.9 GB | 6229dc3804ea |
| model-00005-of-00005.safetensors | Weights | 4.9 GB | 6ab8181eb4b1 |
| config.json | Configuration | 746 B | — |
| generation_config.json | Configuration | 167 B | — |
| model.safetensors.index.json | Configuration | 29.9 KB | — |
| chat_template.jinja | Other | 398 B | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer.json | Tokenizer | 17.1 MB | 5d7cdf4abdcf |
| tokenizer_config.json | Tokenizer | 177.4 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 24.5 GB
Released by Enderman98 through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 24.5 GB |
| 16-bit | 24.5 GB |
| 8-bit | 12.2 GB |
| 4-bit | 6.1 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About andromeda-gguf
How much GPU memory does andromeda-gguf need?
About 29.4 GB at 16-bit and 7.3 GB at 4-bit: the weights (12.2B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run andromeda-gguf 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 andromeda-gguf's context length?
131,072 tokens, from the maximum position embeddings in its published configuration.