Open-weight model
lvr-export-lvr_mmcot_mix_v3_4k_nonema
by Rlyang yrlyrl/lvr-export-lvr_mmcot_mix_v3_4k_nonema
lvr-export-lvr_mmcot_mix_v3_4k_nonema is an open-weight model from Rlyang. It has 14.6B parameters and a 32,768-token context. At 16-bit it needs about 35.1 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 lvr-export-lvr_mmcot_mix_v3_4k_nonema (14.6B 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 | 29.2 GB | 35.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 14.6 GB | 17.5 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 7.3 GB | 8.8 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 19, 2026.
Model Card
The publisher has not written a card for this model.
Configuration
- Architecture
- BagelForConditionalGeneration
- Context length (tokens)
- 32,768
- Layers
- 28
- Hidden size
- 3,584
- Feed-forward size
- 18,944
- Attention heads
- 28
- Key/value heads
- 4
- Vocabulary size
- 152,064
- Sliding window (tokens)
- 131,072
- RoPE base
- 1e+06
- Stored precision
- bfloat16
- Model type
- bagel
Identity and Version
- Repository
- yrlyrl/lvr-export-lvr_mmcot_mix_v3_4k_nonema
- Publisher
- Rlyang
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 14.6B parameters
- Languages
- Not stated by the source
- Revision
- 13600c344c6bb5b92133601466488d31fa0a71f2
- First published
- 2026-10-07
- Last updated
- 2026-10-07
Files and Weights
14 files, 29.6 GB in total. The weights are 2 files totalling 29.5 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| ae.safetensors | Weights | 335.3 MB | afc8e28272cd |
| model.safetensors | Weights | 29.2 GB | 078e9cd3acdf |
| config.json | Configuration | 1.4 KB | — |
| export_info.json | Configuration | 253 B | — |
| generation_config.json | Configuration | 243 B | — |
| llm_config.json | Configuration | 663 B | — |
| preprocessor_config.json | Configuration | 392 B | — |
| vit_config.json | Configuration | 205 B | — |
| MIRROR_COMPLETE | Other | 86 B | — |
| .gitattributes | Repository | 1.5 KB | — |
| merges.txt | Tokenizer | 1.7 MB | — |
| tokenizer.json | Tokenizer | 7.0 MB | — |
| tokenizer_config.json | Tokenizer | 7.3 KB | — |
| vocab.json | Tokenizer | 2.8 MB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 29.5 GB
Released by Rlyang through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 29.5 GB |
| 16-bit | 29.2 GB |
| 8-bit | 14.6 GB |
| 4-bit | 7.3 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About lvr-export-lvr_mmcot_mix_v3_4k_nonema
How much GPU memory does lvr-export-lvr_mmcot_mix_v3_4k_nonema need?
About 35.1 GB at 16-bit and 8.8 GB at 4-bit: the weights (14.6B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run lvr-export-lvr_mmcot_mix_v3_4k_nonema 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 lvr-export-lvr_mmcot_mix_v3_4k_nonema's context length?
32,768 tokens, from the maximum position embeddings in its published configuration.