Model reference · open weights

KD-Tinker

LLMs HuggingFaceH4 Text gen 1 build Licence not stated 21 dl/mo

KD-Tinker is an open-weight language model from Hugging Face. KD-Tinker (BF16) weighs 16.4 GB; the smallest configuration that runs it is 2× RTX 3060 12 GB.

What it is

Released byHugging Face
Released2026-02-03
Parameters8.2B
VRAM16.4 GB for the weights

What it runs on

Memory and cards for KD-Tinker (BF16)

16.4 GBweights, file size
147 MBcache per 1K tokens
753 MBruntime overhead, at least
32,768 tokenscontext max
CardRequests at onceContext maxMemory
8K each32K each
RTX 3060 12 GB … RTX 4060 Ti 16 GB
2 smaller cards
———
RTX 3090 24 GB51all 32K23.4 GB
RTX 4090 24 GB51all 32K23.4 GB
RTX 5090 32 GB112all 32K31.0 GB
L40S 48 GB225all 32K44.0 GB
A100 80 GB5012all 32K78.2 GB
H100 80 GB4611all 32K78.1 GB
RTX PRO 6000 Blackwell 96 GB5914all 32K93.8 GB
DGX Spark (GB10) 128 GB unified7117all 32K107 GB
H200 141 GB9624all 32K138 GB
B200 180 GB12731all 32K176 GB
2× RTX 3060 12 GB
tensor parallel
41all 32K11.6 GB a card
2× RTX 4060 Ti 16 GB
tensor parallel
102all 32K15.4 GB a card
2× RTX 4090 24 GB
tensor parallel
235all 32K23.4 GB a card
2× RTX 3090 24 GB
tensor parallel
235all 32K23.4 GB a card
Memory needed at each load
Requests at once8K tokens each32K tokens each
118.3 GB22.0 GB
523.2 GB41.3 GB
826.8 GB55.8 GB
1636.5 GB94.4 GB
3255.8 GB172 GB
6494.4 GB326 GB

One card, with vLLM's small-card settings.

From the model card

What Hugging Face says about KD-Tinker

Model Details

Model Description

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

  • Developed by: [More Information Needed]
  • Funded by [optional]: [More Information Needed]
  • Shared by [optional]: [More Information Needed]
  • Model type: [More Information Needed]
  • Language(s) (NLP): [More Information Needed]
  • License: [More Information Needed]
  • Finetuned from model [optional]: [More Information Needed]

Model Sources [optional]

  • Repository: [More Information Needed]
  • Paper [optional]: [More Information Needed]
  • Demo [optional]: [More Information Needed]

Uses

Direct Use

[More Information Needed]

Read the full model card

Downstream Use [optional]

[More Information Needed]

Out-of-Scope Use

[More Information Needed]

Bias, Risks, and Limitations

[More Information Needed]

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

Use the code below to get started with the model.

[More Information Needed]

Training Details

Training Data

[More Information Needed]

Training Procedure

Preprocessing [optional]

[More Information Needed]

Training Hyperparameters
  • Training regime: [More Information Needed]
Speeds, Sizes, Times [optional]

[More Information Needed]

Evaluation

Testing Data, Factors & Metrics

Testing Data

[More Information Needed]

Factors

[More Information Needed]

Metrics

[More Information Needed]

Results

[More Information Needed]

Summary

Model Examination [optional]

[More Information Needed]

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

  • Hardware Type: [More Information Needed]
  • Hours used: [More Information Needed]
  • Cloud Provider: [More Information Needed]
  • Compute Region: [More Information Needed]
  • Carbon Emitted: [More Information Needed]

Technical Specifications [optional]

Model Architecture and Objective

[More Information Needed]

Compute Infrastructure

[More Information Needed]

Hardware

[More Information Needed]

Software

[More Information Needed]

Citation [optional]

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Glossary [optional]

[More Information Needed]

More Information [optional]

[More Information Needed]

Model Card Authors [optional]

[More Information Needed]

Model Card Contact

[More Information Needed]

Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms