Mina-MoE-4x1B-RL-Zero is an open-weight model from Bùi Minh Trí, released under llama3.2. It has 3.9B parameters and a 131,072-token context. At 16-bit it needs about 9.4 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index. It draws 201 downloads a month.
Mô hình ngôn ngữ nhỏ phân hóa 4 Chuyên gia (Sparse Mixture of Experts) theo kiến trúc Mixtral 4x1B.
Runs On
What it takes to serve Mina-MoE-4x1B-RL-Zero (3.9B 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 | 7.8 GB | 9.4 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 3.9 GB | 4.7 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 2.0 GB | 2.3 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.
Mina-MoE-4x1B-RL-Zero on every accelerator the SAVRN Index prices, at every precision
Model Card
Mô hình ngôn ngữ nhỏ phân hóa 4 Chuyên gia (Sparse Mixture of Experts) theo kiến trúc Mixtral 4x1B. - Tổng tham số lưu trữ: 3,651,864,576 (~3.65B) - Tham số kích hoạt mỗi token: 1,235,879,936 (1.236B Active FLOPs) - Phiên bản GGUF: Q6K (~2.4 GB) sweet spot, Q80 (~3.8 GB) benchmark
Excerpt from the card by Bùi Minh Trí, licensed llama3.2.
Configuration
- Architecture
- MixtralForCausalLM
- Context length (tokens)
- 131,072
- Layers
- 16
- Hidden size
- 2,048
- Feed-forward size
- 8,192
- Attention heads
- 32
- Key/value heads
- 8
- Head dimension
- 64
- Vocabulary size
- 128,256
- Experts
- 4
- Experts active per token
- 1
- RoPE base
- 10000
- Model type
- mixtral
Identity and Version
- Repository
- Trivnpk/Mina-MoE-4x1B-RL-Zero
- Publisher
- Bùi Minh Trí
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 3.9B parameters
- Languages
- vi, en
- Revision
- e0a1ae19fbf2957cf8316399abfb883415eb3a6d
- First published
- 2026-10-17
- Last updated
- 2026-10-19
Files and Weights
14 files, 19.2 GB in total. The weights are 5 files totalling 19.2 GB in gguf, safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| mina-moe-4x1b-Q2_K.gguf | Weights | 1.5 GB | 3b69e420795b |
| mina-moe-4x1b-Q4_K_M.gguf | Weights | 2.4 GB | 29ca57442aa4 |
| mina-moe-4x1b-Q6_K.gguf | Weights | 3.2 GB | c8be7d0d3351 |
| mina-moe-4x1b-Q8_0.gguf | Weights | 4.2 GB | 9f814ccefd11 |
| model.safetensors | Weights | 7.8 GB | 0dad56da5539 |
| config.json | Configuration | 2.4 KB | — |
| generation_config.json | Configuration | 240 B | — |
| special_tokens_map.json | Configuration | 439 B | — |
| README.md | Documentation | 460 B | — |
| Modelfile | Other | 699 B | — |
| chat_template.jinja | Other | 398 B | — |
| .gitattributes | Repository | 1.8 KB | — |
| tokenizer.json | Tokenizer | 17.2 MB | 57e258c3604c |
| tokenizer_config.json | Tokenizer | 51.1 KB | — |
License and Download
- License
- llama3.2
- Access
- Open weights, no gate
- Download size
- 19.2 GB
Released by Bùi Minh Trí through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 19.2 GB |
| 16-bit | 7.8 GB |
| 8-bit | 3.9 GB |
| 4-bit | 2.0 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About Mina-MoE-4x1B-RL-Zero
How much GPU memory does Mina-MoE-4x1B-RL-Zero need?
About 9.4 GB at 16-bit and 2.3 GB at 4-bit: the weights (3.9B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run Mina-MoE-4x1B-RL-Zero 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 license is Mina-MoE-4x1B-RL-Zero released under?
llama3.2, as its publisher declares it. Read the license text before commercial use.
What is Mina-MoE-4x1B-RL-Zero's context length?
131,072 tokens, from the maximum position embeddings in its published configuration.