Open-weight model
combined_nllb_sanlish_to_bangla_epoch25
by Chandan Hembrom thunderboltc/combined_nllb_sanlish_to_bangla_epoch25
combined_nllb_sanlish_to_bangla_epoch25 is an open-weight model from Chandan Hembrom. It has 615M parameters and a 1,024-token context. At 16-bit it needs about 1.5 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 combined_nllb_sanlish_to_bangla_epoch25 (615M 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 | 1.2 GB | 1.5 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.6 GB | 0.7 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.3 GB | 0.4 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.
Model Card
The publisher has not written a card for this model.
Configuration
- Architecture
- M2M100ForConditionalGeneration
- Context length (tokens)
- 1,024
- Layers
- 12
- Vocabulary size
- 256,206
- Stored precision
- float32
- Model type
- m2m_100
Identity and Version
- Repository
- thunderboltc/combined_nllb_sanlish_to_bangla_epoch25
- Publisher
- Chandan Hembrom
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 615M parameters
- Languages
- Not stated by the source
- Revision
- 8d4585958da7e797affd1faf8b756dc9e563c9b6
- First published
- 2026-09-27
- Last updated
- 2026-09-27
Files and Weights
4 files, 2.5 GB in total. The weights are 2 files totalling 2.5 GB in bin, safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 2.5 GB | f31a1e61fd43 |
| training_args.bin | Weights | 5.8 KB | 2f9844439b99 |
| config.json | Configuration | 897 B | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 2.5 GB
Released by Chandan Hembrom through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 2.5 GB |
| 16-bit | 1.2 GB |
| 8-bit | 0.6 GB |
| 4-bit | 0.3 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About combined_nllb_sanlish_to_bangla_epoch25
How much GPU memory does combined_nllb_sanlish_to_bangla_epoch25 need?
About 1.5 GB at 16-bit and 0.4 GB at 4-bit: the weights (615M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run combined_nllb_sanlish_to_bangla_epoch25 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 combined_nllb_sanlish_to_bangla_epoch25's context length?
1,024 tokens, from the maximum position embeddings in its published configuration.