AU

AutoTriton

AutotritonGGUF by mradermacherUpdated 2025-12-28
Download on Hugging Face
Parameters8.25B
Context64K
Layers32
Architecturellama
Smallest quant0.0 GB
Quick answer

AutoTriton needs about 6.6 GB of memory at Q4_K_M (a 5.1 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 25 quants, from 0.0 GB to 6.8 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

AutoTriton – 8B Llama model specialized for Triton programming

AutoTriton is an 8.25B parameter Llama model trained for Triton kernel generation. It uses supervised fine‑tuning followed by reinforcement learning to optimize kernel performance. The model supports a 65536 token context window and is released under Apache‑2.0.

Good at

  • Triton kernel generation
  • Reinforcement‑learned optimization
  • Large context handling

Limits

  • No vision support
  • Requires 8K context for memory estimates
  • No mixture of experts

Best for

  • Generating Triton code snippets
  • Optimizing GPU kernels
  • Fine‑tuning on custom kernel datasets

Who it’s for. Developers and researchers working on GPU kernel optimization and Triton programming. The model is suitable for those who need automated kernel generation and performance tuning.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.6 GB
Fits Get file →
IQ1_S2.1 GB 3.7 GB
Fits Get file →
IQ1_M2.3 GB 3.8 GB
Fits Get file →
IQ2_XXS2.5 GB 4.1 GB
Fits Get file →
IQ2_XS2.7 GB 4.3 GB
Fits Get file →
IQ2_S2.9 GB 4.5 GB
Fits Get file →
IQ2_M3.1 GB 4.6 GB
Fits Get file →
Q2_K_S3.1 GB 4.7 GB
Fits Get file →
Q2_K3.3 GB 4.9 GB
Fits Get file →
IQ3_XXS3.4 GB 5.0 GB
Fits Get file →
IQ3_XS3.7 GB 5.2 GB
Fits Get file →
Q3_K_S3.8 GB 5.4 GB
Fits Get file →
IQ3_S3.8 GB 5.4 GB
Fits Get file →
IQ3_M3.9 GB 5.5 GB
Fits Get file →
Q3_K_M4.2 GB 5.7 GB
Fits Get file →
Q3_K_L4.5 GB 6.0 GB
Fits Get file →
IQ4_XS4.6 GB 6.2 GB
Fits Get file →
Q4_04.8 GB 6.4 GB
Fits Get file →
IQ4_NL4.8 GB 6.4 GB
Fits Get file →
Q4_K_S4.8 GB 6.4 GB
Fits Get file →
Q4_K_M5.1 GB 6.6 GB
Fits Get file →
Q4_15.3 GB 6.9 GB
Fits Get file →
Q5_K_S5.8 GB 7.3 GB
Tight Get file →
Q5_K_M5.9 GB 7.5 GB
Tight Get file →
Q6_K6.8 GB 8.3 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (2.13 GB, 3.7 GB memory) or Q2_K (3.3 GB, 4.9 GB memory). If 12 GB VRAM is available, Q3_K_M (4.15 GB, 5.7 GB memory) or Q4_K_M (5.07 GB, 6.6 GB memory) provide better quality. Larger models like Q6_K (6.78 GB, 8.3 GB memory) need 16 GB VRAM or more.

What GPU do you need for AutoTriton?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is IQ1_M (2.3 GB file, about 3.8 GB in use).
  • 6 GB VRAM: the best quant that fits is Q3_K_L (4.5 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (5.9 GB file, about 7.5 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (6.8 GB file, about 8.3 GB in use).

Which AutoTriton quant should you choose?

Q4_K_M is the usual starting point for AutoTriton: it balances file size and quality well. Here it is a 5.1 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters8.25B
Layers32
Trained context65,536 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
Licenseapache-2.0
Downloads (HF)1,294
Last updated2025-12-28

Frequently asked questions about AutoTriton

How much VRAM does AutoTriton need?

About 6.6 GB at Q4_K_M with an 8K context window. That is the 5.1 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run AutoTriton on an 8 GB GPU?

Yes, with Q5_K_M: the 5.9 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of AutoTriton GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 2.1 GB, IQ1_M is 2.3 GB, IQ2_XXS is 2.5 GB, IQ2_XS is 2.7 GB, IQ2_S is 2.9 GB and 19 more.

What context length does AutoTriton support?

The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download AutoTriton GGUF?

The files are on Hugging Face in the mradermacher/AutoTriton-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does AutoTriton use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run AutoTriton on 8 GB VRAM?

Yes, use a quant such as IQ1_S or Q2_K which fit within 8 GB VRAM and require about 4 GB of RAM.

Does AutoTriton support vision tasks?

No, the model has no vision capabilities.

What license applies to AutoTriton?

The model is released under the Apache‑2.0 license.

Other GGUFs of AutoTriton

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Autotriton models

All Autotriton →

Other small models

All small models →