AS

ASTRA 32B Thinking v1

AstraGGUF by mradermacherUpdated 2026-01-24
Download on Hugging Face
Parameters32.8B
Context130K
Layers64
Architectureqwen3
Smallest quant0.0 GB
Quick answer

ASTRA 32B Thinking v1 needs about 22.4 GB of memory at Q4_K_M (a 19.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 24 quants, from 0.0 GB to 26.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

ASTRA 32B Thinking v1 – a 32.8B parameter Qwen3 model optimized for tool‑augmented reasoning

ASTRA 32B Thinking v1 is a 32.8B parameter model based on Qwen3. It is fine‑tuned for multi‑step reasoning and tool use, with a trained context of 133120 tokens. The model is released under the apache‑2.0 license.

Good at

  • Multi‑step reasoning
  • Tool‑augmented tasks
  • Structured agentic decision‑making

Limits

  • No vision support
  • Requires large VRAM for full precision
  • No mixed‑expert support

Best for

  • Complex tool‑chain generation
  • Agentic task planning
  • Long‑context reasoning

Who it’s for. Developers building AI agents that need robust tool use and multi‑step reasoning. Researchers exploring agentic LLMs may also find this model useful.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 2.7 GB
Fits Get file →
IQ1_S7.3 GB 10.0 GB
Too big Get file →
IQ1_M8.0 GB 10.6 GB
Too big Get file →
IQ2_XXS9.0 GB 11.7 GB
Too big Get file →
IQ2_XS10.0 GB 12.6 GB
Too big Get file →
IQ2_S10.5 GB 13.2 GB
Too big Get file →
IQ2_M11.4 GB 14.0 GB
Too big Get file →
Q2_K_S11.5 GB 14.1 GB
Too big Get file →
Q2_K12.3 GB 15.0 GB
Too big Get file →
IQ3_XXS12.8 GB 15.5 GB
Too big Get file →
IQ3_XS13.7 GB 16.4 GB
Too big Get file →
Q3_K_S14.4 GB 17.0 GB
Too big Get file →
IQ3_S14.4 GB 17.1 GB
Too big Get file →
IQ3_M14.9 GB 17.6 GB
Too big Get file →
Q3_K_M16.0 GB 18.6 GB
Too big Get file →
Q3_K_L17.3 GB 20.0 GB
Too big Get file →
IQ4_XS17.7 GB 20.3 GB
Too big Get file →
Q4_018.7 GB 21.4 GB
Too big Get file →
Q4_K_S18.8 GB 21.4 GB
Too big Get file →
Q4_K_M19.8 GB 22.4 GB
Too big Get file →
Q4_120.6 GB 23.3 GB
Too big Get file →
Q5_K_S22.6 GB 25.3 GB
Too big Get file →
Q5_K_M23.2 GB 25.9 GB
Too big Get file →
Q6_K26.9 GB 29.5 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (file size 7.32 GB, memory 10 GB at 8k context). With 12 GB VRAM, Q4_K_M (19.76 GB, 22.4 GB memory) is suitable. For 16 GB VRAM, Q5_K_M (23.21 GB, 25.9 GB memory) offers higher quality. Estimates are approximate.

What GPU do you need for ASTRA 32B Thinking v1?

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 the main file (0.0 GB file, about 2.7 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ2_XXS (9.0 GB file, about 11.7 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_XXS (12.8 GB file, about 15.5 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_1 (20.6 GB file, about 23.3 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (26.9 GB file, about 29.5 GB in use).

Which ASTRA 32B Thinking v1 quant should you choose?

Q4_K_M is the usual starting point for ASTRA 32B Thinking v1: it balances file size and quality well. Here it is a 19.8 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
Parameters32.8B
Layers64
Trained context133,120 tokens
KV cache (fp16)256 KB per token

Source

Quantized bymradermacher
FamilyAstra
Licenseapache-2.0
Downloads (HF)394
Last updated2026-01-24

Frequently asked questions about ASTRA 32B Thinking v1

How much VRAM does ASTRA 32B Thinking v1 need?

About 22.4 GB at Q4_K_M with an 8K context window. That is the 19.8 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 ASTRA 32B Thinking v1 on an 8 GB GPU?

Yes, with the smaller files: the 0.0 GB file needs about 2.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of ASTRA 32B Thinking v1 GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 7.3 GB, IQ1_M is 8.0 GB, IQ2_XXS is 9.0 GB, IQ2_XS is 10.0 GB, IQ2_S is 10.5 GB and 18 more.

What context length does ASTRA 32B Thinking v1 support?

The GGUF header lists a trained context length of 133,120 tokens (130K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download ASTRA 32B Thinking v1 GGUF?

The files are on Hugging Face in the mradermacher/ASTRA-32B-Thinking-v1-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 ASTRA 32B Thinking v1 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 ASTRA 32B Thinking v1 on 8 GB VRAM?

Use the IQ1_S quant, which requires about 10 GB of VRAM at 8k context. It will fit on 8 GB with some swapping.

Does the model support vision?

No, the model has no vision capabilities.

What license does the model use?

The model is released under the apache‑2.0 license.

Other GGUFs of ASTRA-32B-Thinking-v1

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Astra models

All Astra →

Other medium models

All medium models →