KenT_0.5B_LLMs_pt is an open-weight model from Nguyễn Quôc Khánh, released under other. It has 465M parameters. At 16-bit it needs about 1.1 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
Copyright © 2026 Nguyễn Quốc Khánh (@KenteaKe11). All rights reserved. from transformers import AutoTokenizer, AutoModelForCausalLM repo = "KenteaKe11/KenT0.5BLLMspt" tok = AutoTokenizer.frompretrained(repo) model = AutoModelForCausalLM.frompretrained(repo…
Runs On
What it takes to serve KenT_0.5B_LLMs_pt (465M 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 | 0.9 GB | 1.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.5 GB | 0.6 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.2 GB | 0.3 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.
KenT_0.5B_LLMs_pt on every accelerator the SAVRN Index prices, at every precision
Model Card
Copyright © 2026 Nguyễn Quốc Khánh (@KenteaKe11). All rights reserved. from transformers import AutoTokenizer, AutoModelForCausalLM repo = "KenteaKe11/KenT0.5BLLMspt" tok = AutoTokenizer.frompretrained(repo) model = AutoModelForCausalLM.frompretrained(repo, trustremotecode=True) inputs = tok("Ha Noi is the capital of Vietnam.", returntensors="pt") out = model.generate(inputs, maxnewtokens=64, temperature=0.7, topk=50, topp=0.9) print(tok.decode(out[0], skipspecialtokens=True))
Excerpt from the card by Nguyễn Quôc Khánh, licensed other.
Configuration
- Architecture
- KenTForCausalLM
- Key/value heads
- 8
- Head dimension
- 128
- Vocabulary size
- 50,257
- RoPE base
- 10000
- Model type
- kent
Identity and Version
- Repository
- KenteaKe11/KenT_0.5B_LLMs_pt
- Publisher
- Nguyễn Quôc Khánh
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 465M parameters
- Languages
- vi, en
- Revision
- ce442da37a501631820d426f787a4d9706eae688
- First published
- 2026-10-13
- Last updated
- 2026-10-14
Files and Weights
9 files, 1.9 GB in total. The weights are 1 file totalling 1.9 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 1.9 GB | 1d0b618923a2 |
| config.json | Configuration | 1.1 KB | — |
| kent_model.py | Configuration | 12.4 KB | — |
| training_state.json | Configuration | 138 B | — |
| LICENSE | Documentation | 18.0 KB | — |
| README.md | Documentation | 800 B | — |
| .gitattributes | Repository | 1.5 KB | — |
| tokenizer.json | Tokenizer | 3.6 MB | — |
| tokenizer_config.json | Tokenizer | 326 B | — |
License and Download
- License
- other
- Access
- Open weights, no gate
- Download size
- 1.9 GB
Released by Nguyễn Quôc Khánh through its official repository on Hugging Face. Read the license.
Built From
- Trained on (disclosed) wikipedia
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 1.9 GB |
| 16-bit | 0.9 GB |
| 8-bit | 0.5 GB |
| 4-bit | 0.2 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About KenT_0.5B_LLMs_pt
How much GPU memory does KenT_0.5B_LLMs_pt need?
About 1.1 GB at 16-bit and 0.3 GB at 4-bit: the weights (465M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run KenT_0.5B_LLMs_pt 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 KenT_0.5B_LLMs_pt released under?
other, as its publisher declares it. Read the license text before commercial use.