Open-weight model
04.1-Ministral-3-14B-Reasoning-2512-4bit-NF4-7.32GB
by Anar Zan AnarZan/04.1-Ministral-3-14B-Reasoning-2512-4bit-NF4-7.32GB
04.1-Ministral-3-14B-Reasoning-2512-4bit-NF4-7.32GB is an open-weight model from Anar Zan. It has 13.3B parameters and a 262,144-token context. At 16-bit it needs about 31.9 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 04.1-Ministral-3-14B-Reasoning-2512-4bit-NF4-7.32GB (13.3B 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 | 26.5 GB | 31.9 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 13.3 GB | 15.9 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 6.6 GB | 8.0 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 23, 2026.
Model Card
The publisher has not written a card for this model.
Configuration
- Architecture
- Mistral3Model
- Context length (tokens)
- 262,144
- Layers
- 40
- Hidden size
- 5,120
- Feed-forward size
- 16,384
- Attention heads
- 32
- Key/value heads
- 8
- Head dimension
- 128
- Vocabulary size
- 131,072
- Model type
- mistral3
- Quantization
- bitsandbytes
Identity and Version
- Repository
- AnarZan/04.1-Ministral-3-14B-Reasoning-2512-4bit-NF4-7.32GB
- Publisher
- Anar Zan
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 13.3B parameters
- Languages
- Not stated by the source
- Revision
- dfbb5433e0529aed67162c709df25faf0cc3674e
- First published
- 2026-10-01
- Last updated
- 2026-10-01
Files and Weights
6 files, 7.9 GB in total. The weights are 1 file totalling 7.8 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 7.8 GB | b995cbbfa12b |
| config.json | Configuration | 2.2 KB | — |
| chat_template.jinja | Other | 12.2 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer.json | Tokenizer | 17.1 MB | 577575622324 |
| tokenizer_config.json | Tokenizer | 21.3 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 7.8 GB
Released by Anar Zan through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 7.8 GB |
| 16-bit | 26.5 GB |
| 8-bit | 13.3 GB |
| 4-bit | 6.6 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About 04.1-Ministral-3-14B-Reasoning-2512-4bit-NF4-7.32GB
How much GPU memory does 04.1-Ministral-3-14B-Reasoning-2512-4bit-NF4-7.32GB need?
About 31.9 GB at 16-bit and 8 GB at 4-bit: the weights (13.3B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run 04.1-Ministral-3-14B-Reasoning-2512-4bit-NF4-7.32GB 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 04.1-Ministral-3-14B-Reasoning-2512-4bit-NF4-7.32GB's context length?
262,144 tokens, from the maximum position embeddings in its published configuration.