Runs On
What it takes to serve b-58m (58M 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 | 0.1 GB | 0.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.1 GB | 0.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.0 GB | 0.0 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
The publisher has not written a card for this model.
Configuration
- Architecture
- FHN_T4Max_150M
- Context length (tokens)
- 512
- Layers
- 12
- Hidden size
- 768
- Vocabulary size
- 1,536
- Stored precision
- float16
- Model type
- fhn_concept_gau
Identity and Version
- Repository
- aixk/b-58m
- Publisher
- Isai Lab
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 58M parameters
- Languages
- Not stated by the source
- Revision
- 301ceaa9ab8400cd5df40291777985936d593781
- First published
- 2026-09-16
- Last updated
- 2026-09-18
Files and Weights
21 files, 1.8 GB in total. The weights are 3 files totalling 1.5 GB in pt, safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| checkpoint_step_128000.pt | Weights | 689.2 MB | cb426264f80d |
| checkpoint_step_129000.pt | Weights | 689.2 MB | 0e301cbb1f78 |
| model.safetensors | Weights | 116.4 MB | 65b4adbe76ac |
| config.json | Configuration | 350 B | — |
| vlite_manifest.json | Configuration | 896 B | — |
| model.vlite | Other | 28.5 MB | 2e4b976a9c46 |
| model_full_int1.vlite | Other | 14.7 MB | f2fd3e428ca3 |
| model_full_int2.vlite | Other | 21.7 MB | 45681a789f12 |
| model_full_int3.vlite | Other | 28.6 MB | 3b68d5bf0fa9 |
| model_full_int4.vlite | Other | 35.5 MB | daa900775670 |
| model_micro_int1.vlite | Other | 25.8 MB | 95e1f9e9d90f |
| model_micro_int2.vlite | Other | 28.5 MB | 2e4b976a9c46 |
| model_micro_int3.vlite | Other | 31.0 MB | 53f5d5dc0ac8 |
| model_micro_int4.vlite | Other | 33.1 MB | 7a33511d8e70 |
| model_shared.vlite | Other | 24.0 MB | 8df3b0b7778b |
| model_shared_int1.vlite | Other | 10.1 MB | bd841d4dd668 |
| model_shared_int2.vlite | Other | 14.7 MB | ccee5cd516b3 |
| model_shared_int3.vlite | Other | 19.4 MB | 11292fa9596e |
| model_shared_int4.vlite | Other | 24.0 MB | 8df3b0b7778b |
| .gitattributes | Repository | 2.3 KB | — |
| tokenizer_state.json | Tokenizer | 275.2 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 1.5 GB
Released by Isai Lab through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 1.5 GB |
| 16-bit | 0.1 GB |
| 8-bit | 0.1 GB |
| 4-bit | 0.0 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About b-58m
How much GPU memory does b-58m need?
About 0.1 GB at 16-bit and 0 GB at 4-bit: the weights (58M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run b-58m 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 b-58m's context length?
512 tokens, from the maximum position embeddings in its published configuration.