deepseek-moe-16b-base_80-mobe is an open-weight model from Zhendong Mi. It has 8.4B parameters and a 4,096-token context. At 16-bit it needs about 20.2 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 deepseek-moe-16b-base_80-mobe (8.4B 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 | 16.8 GB | 20.2 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 8.4 GB | 10.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 4.2 GB | 5.0 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 Oct 20, 2026.
deepseek-moe-16b-base_80-mobe on every accelerator the SAVRN Index prices, at every precision
Model Card
The publisher has not written a card for this model.
Configuration
- Architecture
- DeepseekForCausalLM
- Context length (tokens)
- 4,096
- Layers
- 28
- Hidden size
- 2,048
- Feed-forward size
- 10,944
- Attention heads
- 16
- Key/value heads
- 16
- Vocabulary size
- 102,400
- Routed experts
- 64
- Experts active per token
- 6
- RoPE base
- 10,000
- Stored precision
- bfloat16
- Model type
- deepseek
Identity and Version
- Repository
- zmi/deepseek-moe-16b-base_80-mobe
- Publisher
- Zhendong Mi
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 8.4B parameters
- Languages
- Not stated by the source
- Revision
- 07bc0b41a371cfdf28eaa53d057e03f3d5156550
- First published
- 2026-10-03
- Last updated
- 2026-10-03
Files and Weights
12 files, 16.8 GB in total. The weights are 4 files totalling 16.8 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model-00001-of-00004.safetensors | Weights | 5.0 GB | 9e44c4a3bb43 |
| model-00002-of-00004.safetensors | Weights | 5.0 GB | 21e9f8385308 |
| model-00003-of-00004.safetensors | Weights | 5.0 GB | 9dc0a74d728c |
| model-00004-of-00004.safetensors | Weights | 1.8 GB | 194fb7572750 |
| config.json | Configuration | 1.2 KB | — |
| configuration_deepseek.py | Configuration | 10.2 KB | — |
| generation_config.json | Configuration | 121 B | — |
| model.safetensors.index.json | Configuration | 595.2 KB | — |
| special_tokens_map.json | Configuration | 482 B | — |
| .gitattributes | Repository | 1.5 KB | — |
| tokenizer.json | Tokenizer | 7.5 MB | — |
| tokenizer_config.json | Tokenizer | 3.1 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 16.8 GB
Released by Zhendong Mi through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 16.8 GB |
| 16-bit | 16.8 GB |
| 8-bit | 8.4 GB |
| 4-bit | 4.2 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About deepseek-moe-16b-base_80-mobe
How much GPU memory does deepseek-moe-16b-base_80-mobe need?
About 20.2 GB at 16-bit and 5 GB at 4-bit: the weights (8.4B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run deepseek-moe-16b-base_80-mobe 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 deepseek-moe-16b-base_80-mobe's context length?
4,096 tokens, from the maximum position embeddings in its published configuration.