AT

ATLAS 8B Instruct

AtlasGGUF by mradermacherUpdated 2025-12-04
Download on Hugging Face
Parameters8.19B
Context40K
Layers36
Architectureqwen3
Smallest quant0.0 GB
Quick answer

ATLAS 8B Instruct needs about 6.7 GB of memory at Q4_K_M (a 5.0 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 6.7 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

ATLAS 8B Instruct – a teaching‑focused Qwen3 model

ATLAS 8B Instruct is a 8.19 B‑parameter model fine‑tuned for structured teaching content. It is the first phase of the ATLAS framework and serves as the base for subsequent reinforcement learning. The model is released in GGUF format for local inference.

Good at

  • structured teaching content
  • reasoning and tool usage
  • SFT‑based pedagogy

Limits

  • not a general chat model
  • no vision support
  • trained on 8192‑token context

Best for

  • educational content generation
  • research on teaching models
  • pre‑training for RL agents

Who it’s for. Researchers and developers building adaptive teaching systems or experimenting with the ATLAS training pipeline. The model is ideal for those who need a foundation for reinforcement learning or structured content generation.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.7 GB
Fits Get file →
IQ1_S2.1 GB 3.8 GB
Fits Get file →
IQ1_M2.3 GB 4.0 GB
Fits Get file →
IQ2_XXS2.5 GB 4.2 GB
Fits Get file →
IQ2_XS2.7 GB 4.4 GB
Fits Get file →
IQ2_S2.9 GB 4.6 GB
Fits Get file →
IQ2_M3.1 GB 4.8 GB
Fits Get file →
Q2_K_S3.1 GB 4.8 GB
Fits Get file →
Q2_K3.3 GB 5.0 GB
Fits Get file →
IQ3_XXS3.4 GB 5.1 GB
Fits Get file →
IQ3_XS3.6 GB 5.3 GB
Fits Get file →
Q3_K_S3.8 GB 5.5 GB
Fits Get file →
IQ3_S3.8 GB 5.5 GB
Fits Get file →
IQ3_M3.9 GB 5.6 GB
Fits Get file →
Q3_K_M4.1 GB 5.8 GB
Fits Get file →
Q3_K_L4.4 GB 6.1 GB
Fits Get file →
IQ4_XS4.6 GB 6.3 GB
Fits Get file →
Q4_04.8 GB 6.5 GB
Fits Get file →
IQ4_NL4.8 GB 6.5 GB
Fits Get file →
Q4_K_S4.8 GB 6.5 GB
Fits Get file →
Q4_K_M5.0 GB 6.7 GB
Fits Get file →
Q4_15.2 GB 7.0 GB
Fits Get file →
Q5_K_S5.7 GB 7.4 GB
Tight Get file →
Q5_K_M5.9 GB 7.6 GB
Tight Get file →
Q6_K6.7 GB 8.4 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (2.12 GB, 3.8 GB memory) or IQ1_M (2.26 GB, 4 GB memory). If 12 GB is available, IQ2_S (2.86 GB, 4.6 GB memory) or Q2_K (3.28 GB, 5 GB memory) are suitable. Higher‑quality quants like Q4_K_M (5.03 GB, 6.7 GB memory) require 16 GB or more.

What GPU do you need for ATLAS 8B Instruct?

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 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q3_K_M (4.1 GB file, about 5.8 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (5.9 GB file, about 7.6 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (6.7 GB file, about 8.4 GB in use).

Which ATLAS 8B Instruct quant should you choose?

Q4_K_M is the usual starting point for ATLAS 8B Instruct: it balances file size and quality well. Here it is a 5.0 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

Architectureqwen3
Parameters8.19B
Layers36
Trained context40,960 tokens
KV cache (fp16)144 KB per token

Source

Quantized bymradermacher
FamilyAtlas
Licenseapache-2.0
Downloads (HF)726
Last updated2025-12-04

Frequently asked questions about ATLAS 8B Instruct

How much VRAM does ATLAS 8B Instruct need?

About 6.7 GB at Q4_K_M with an 8K context window. That is the 5.0 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 ATLAS 8B Instruct on an 8 GB GPU?

Yes, with Q5_K_M: the 5.9 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of ATLAS 8B Instruct 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 ATLAS 8B Instruct support?

The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.

Where can I download ATLAS 8B Instruct GGUF?

The files are on Hugging Face in the mradermacher/ATLAS-8B-Instruct-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 ATLAS 8B Instruct 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 ATLAS 8B Instruct on 8 GB VRAM?

Yes, the IQ1_S quant uses 2.12 GB file size and needs about 3.8 GB VRAM at 8k context. It fits within an 8 GB budget with headroom.

Does the model support image inputs?

No, ATLAS 8B Instruct has no vision capability and is trained only on text.

Is the model suitable for general chat?

No, it is designed for teaching content generation and is not intended for conversational use.

Other GGUFs of ATLAS-8B-Instruct

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Atlas models

All Atlas →

Other small models

All small models →