m-056f62fd is an open-weight model from Dsa. It has 25.8B parameters and a 262,144-token context. At 16-bit it needs about 62 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 m-056f62fd (25.8B 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 | 51.6 GB | 62.0 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 25.8 GB | 31.0 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 12.9 GB | 15.5 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 Oct 18, 2026.
m-056f62fd on every accelerator the SAVRN Index prices, at every precision
Model Card
The publisher has not written a card for this model.
Configuration
- Architecture
- DiffusionGemmaForBlockDiffusion
- Context length (tokens)
- 262,144
- Layers
- 30
- Hidden size
- 2,816
- Feed-forward size
- 2,112
- Attention heads
- 16
- Key/value heads
- 8
- Head dimension
- 256
- Vocabulary size
- 262,144
- Experts
- 128
- Sliding window (tokens)
- 1,024
- Model type
- diffusion_gemma
Identity and Version
- Repository
- dasLOL/m-056f62fd
- Publisher
- Dsa
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 25.8B parameters
- Languages
- Not stated by the source
- Revision
- 6b4275eef0a9721954264bc5004b95d625e00080
- First published
- 2026-10-08
- Last updated
- 2026-10-08
Files and Weights
14 files, 51.6 GB in total. The weights are 11 files totalling 51.6 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model-00001-of-00011.safetensors | Weights | 4.7 GB | 7a0caa88a368 |
| model-00002-of-00011.safetensors | Weights | 4.9 GB | 401ee2865c71 |
| model-00003-of-00011.safetensors | Weights | 4.9 GB | d0c2f507cb01 |
| model-00004-of-00011.safetensors | Weights | 4.9 GB | 2e9ed1a7ad8a |
| model-00005-of-00011.safetensors | Weights | 4.9 GB | 3afe227ba8d1 |
| model-00006-of-00011.safetensors | Weights | 4.9 GB | b3183eb27845 |
| model-00007-of-00011.safetensors | Weights | 4.9 GB | 2cb01b81d97d |
| model-00008-of-00011.safetensors | Weights | 4.9 GB | d6088e286a03 |
| model-00009-of-00011.safetensors | Weights | 4.9 GB | 2a1d0ba88014 |
| model-00010-of-00011.safetensors | Weights | 4.9 GB | 506f61346356 |
| model-00011-of-00011.safetensors | Weights | 2.8 GB | 024cf7725156 |
| config.json | Configuration | 3.5 KB | — |
| model.safetensors.index.json | Configuration | 104.7 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 51.6 GB
Released by Dsa through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 51.6 GB |
| 16-bit | 51.6 GB |
| 8-bit | 25.8 GB |
| 4-bit | 12.9 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About m-056f62fd
How much GPU memory does m-056f62fd need?
About 62 GB at 16-bit and 15.5 GB at 4-bit: the weights (25.8B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run m-056f62fd 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 m-056f62fd's context length?
262,144 tokens, from the maximum position embeddings in its published configuration.