QW

Qwen3 32B Kimi K2 Thinking Distill

QwenGGUF by mradermacherUpdated 2026-02-06
Download on Hugging Face
Parameters32.8B
Context40K
Layers64
Architectureqwen3
Smallest quant0.0 GB
Quick answer

Qwen3 32B Kimi K2 Thinking Distill 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.

Qwen3 32B Kimi K2 Thinking Distill – a 32.8B reasoning model in GGUF format

Qwen3 32B Kimi K2 Thinking Distill is a 32.8B parameter model trained on 1000 high reasoning examples from the Kimi-K2-Thinking dataset. It supports reasoning and tool use and is available in multiple quantizations for different memory budgets.

Good at

  • Reasoning
  • Tool use
  • Deep research

Limits

  • No vision support
  • Requires 8k context for full performance
  • Apache‑2.0 license

Best for

  • Coding assistance
  • Mathematical problem solving
  • Research summarization

Who it’s for. Developers and researchers who need a large language model with strong reasoning and tool‑using capabilities. The model is suitable for local deployment via llama.cpp or similar GGUF‑compatible runtimes.

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, the IQ1_S quant (~7.32 GB file, 10 GB memory at 8k context) is recommended. If 12‑GB VRAM is available, IQ2_S (~9.95 GB file, 12.6 GB memory) offers a balance of size and performance. For larger GPUs, Q4_K_M (~19.76 GB file, 22.4 GB memory) provides higher quality.

What GPU do you need for Qwen3 32B Kimi K2 Thinking Distill?

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 Qwen3 32B Kimi K2 Thinking Distill quant should you choose?

Q4_K_M is the usual starting point for Qwen3 32B Kimi K2 Thinking Distill: 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 context40,960 tokens
KV cache (fp16)256 KB per token

Source

Quantized bymradermacher
FamilyQwen
Licenseapache-2.0
Downloads (HF)663
Last updated2026-02-06

Frequently asked questions about Qwen3 32B Kimi K2 Thinking Distill

How much VRAM does Qwen3 32B Kimi K2 Thinking Distill 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 Qwen3 32B Kimi K2 Thinking Distill 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 Qwen3 32B Kimi K2 Thinking Distill 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 Qwen3 32B Kimi K2 Thinking Distill support?

The GGUF header lists a trained context length of 40,960 tokens (40K). 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 Qwen3 32B Kimi K2 Thinking Distill GGUF?

The files are on Hugging Face in the mradermacher/Qwen3-32B-Kimi-K2-Thinking-Distill-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 Qwen3 32B Kimi K2 Thinking Distill 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 this model on 8 GB VRAM?

The IQ1_S quant uses about 10 GB of VRAM at 8k context, so 8 GB is insufficient. Use a smaller quant or increase VRAM.

Does the model support vision tasks?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of Qwen3-32B-Kimi-K2-Thinking-Distill

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Qwen models

All Qwen →

Other medium models

All medium models →