Emomni-v1-small is an open-weight model from Jotakak, released under Apache License 2.0. It has 3.1B parameters. At 16-bit it needs about 7.5 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index. It draws 5 downloads a month.
Complete Emomni checkpoint with global LoRA merged into the model weights. The checkpoint includes its tokenizer, chat template, Whisper feature extractor, and generation configuration. No separate LoRA adapter is required.
Runs On
What it takes to serve Emomni-v1-small (3.1B 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 | 6.2 GB | 7.5 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 3.1 GB | 3.7 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 1.6 GB | 1.9 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 23, 2026.
Emomni-v1-small on every accelerator the SAVRN Index prices, at every precision
Model Card
By Jotakak, published under apache-2.0, revision 5937d970b50b.
Complete Emomni checkpoint with global LoRA merged into the model weights. The checkpoint includes its tokenizer, chat template, Whisper feature extractor, and generation configuration. No separate LoRA adapter is required. The global-LoRA checkpoint is now distributed with its adapters already merged. Use the Emomni-v1 code: The custom model is loaded by src.modelingemomni.EmomniModel, rather than the generic AutoModelForCausalLM loader. The original export verified all 543 saved tensors and matching text/audio greedy outputs after reloading. These checks verify checkpoint serialization; they are not a new quality benchmark.
Read Jotakak's full model card
Emomni-v1 Small — merged BF16
Complete Emomni checkpoint with global LoRA merged into the model weights. The checkpoint includes its tokenizer, chat template, Whisper feature extractor, and generation configuration. No separate LoRA adapter is required.
The global-LoRA checkpoint is now distributed with its adapters already merged.
Use the Emomni-v1 code:
bash scripts/run_serve.sh --model Jotakak/Emomni-v1-small
The custom model is loaded by src.modeling_emomni.EmomniModel, rather than
the generic AutoModelForCausalLM loader.
The original export verified all 543 saved tensors and matching text/audio greedy outputs after reloading. These checks verify checkpoint serialization; they are not a new quality benchmark.
Configuration
- Architecture
- EmomniModel
- Model type
- emomni-v1
Identity and Version
- Repository
- Jotakak/Emomni-v1-small
- Publisher
- Jotakak
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 3.1B parameters
- Languages
- Not stated by the source
- Revision
- 5937d970b50b10f47eef49e6d297021922861d19
- First published
- 2026-03-05
- Last updated
- 2026-10-11
Files and Weights
15 files, 6.9 GB in total. The weights are 2 files totalling 6.9 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model-00001-of-00002.safetensors | Weights | 4.0 GB | 7554d408a6bc |
| model-00002-of-00002.safetensors | Weights | 2.9 GB | 56b6d27b91c5 |
| added_tokens.json | Configuration | 605 B | — |
| config.json | Configuration | 7.5 KB | — |
| generation_config.json | Configuration | 270 B | — |
| model.safetensors.index.json | Configuration | 49.6 KB | — |
| preprocessor_config.json | Configuration | 356 B | — |
| special_tokens_map.json | Configuration | 613 B | — |
| README.md | Documentation | 891 B | — |
| chat_template.jinja | Other | 2.5 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| merges.txt | Tokenizer | 1.7 MB | — |
| tokenizer.json | Tokenizer | 11.4 MB | 9c5ae00e602b |
| tokenizer_config.json | Tokenizer | 4.7 KB | — |
| vocab.json | Tokenizer | 2.8 MB | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 6.9 GB
Released by Jotakak through its official repository on Hugging Face. Read the license.
Built From
- Derived from Qwen/Qwen2.5-3B-Instruct
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 6.9 GB |
| 16-bit | 6.2 GB |
| 8-bit | 3.1 GB |
| 4-bit | 1.6 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Built on This Model
- Quantized fromEmomni-v1-small-bnb-4bit
- Derived fromEmomni-v1-small-bnb-4bit
Questions About Emomni-v1-small
How much GPU memory does Emomni-v1-small need?
About 7.5 GB at 16-bit and 1.9 GB at 4-bit: the weights (3.1B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run Emomni-v1-small 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.
Can I use Emomni-v1-small commercially?
Yes. Emomni-v1-small is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.