DE

Qwen3 4B Thinking 2507 DeepSeek v3.2 Speciale Math Distill

DeepSeekGGUF by TeichAIUpdated 2025-12-07
Download on Hugging Face
Parameters4.02B
Context256K
Layers36
Architectureqwen3
Smallest quant1.9 GB
Quick answer

Qwen3 4B Thinking 2507 DeepSeek v3.2 Speciale Math Distill needs about 4.2 GB of memory at Q4_K_M (a 2.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 8 quants, from 1.9 GB (Q3_K_S) to 8.1 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

Qwen3 4B Thinking 2507 DeepSeek v3.2 Speciale Math Distill – a 4.02B parameter reasoning model

Qwen3-4B-Thinking-2507-DeepSeek-v3.2-Speciale-Math-Distill is a 4.02 billion‑parameter LLM fine‑tuned for reasoning and tool use. It supports a 262,144‑token context window and is released under the Apache‑2.0 license.

Good at

  • Reasoning tasks
  • Tool‑based workflows
  • Math‑centric queries

Limits

  • No vision support
  • Large context requires significant VRAM
  • No mixture‑of‑experts

Best for

  • Complex problem solving
  • Automated tool integration
  • Educational math assistance

Who it’s for. Developers and researchers needing a lightweight reasoning model with a large context window. The model is suitable for applications that require tool usage and mathematical reasoning without multimodal input.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S1.9 GB 3.6 GB
Fits Get file →
Q3_K_M2.1 GB 3.8 GB
Fits Get file →
IQ4_NL2.4 GB 4.1 GB
Fits Get file →
Q4_K_M2.5 GB 4.2 GB
Fits Get file →
Q8_04.3 GB 6.0 GB
Fits Get file →
Q8_04.3 GB 6.0 GB
Fits Get file →
F168.1 GB 9.8 GB
Too big Get file →
BF168.1 GB 9.8 GB
Too big Get file →

For 8 GB VRAM, use Q3_K_S (1.89 GB, ~3.6 GB memory) or Q3_K_M (2.08 GB, ~3.8 GB memory). For 12 GB VRAM, Q4_K_M (2.5 GB, ~4.2 GB memory) is a good balance. Higher precision Q8_0 (4.28 GB, ~6 GB memory) or F16/BF16 (8.05 GB, ~9.8 GB memory) requires more VRAM.

What GPU do you need for Qwen3 4B Thinking 2507 DeepSeek v3.2 Speciale Math 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 Q3_K_M (2.1 GB file, about 3.8 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (4.3 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.3 GB file, about 6.0 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (8.1 GB file, about 9.8 GB in use).

Which Qwen3 4B Thinking 2507 DeepSeek v3.2 Speciale Math Distill quant should you choose?

Q4_K_M is the usual starting point for Qwen3 4B Thinking 2507 DeepSeek v3.2 Speciale Math Distill: it balances file size and quality well. Here it is a 2.5 GB file.

The Q8_0 file is 4.3 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q3_K_S at 1.9 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3
Parameters4.02B
Layers36
Trained context262,144 tokens
KV cache (fp16)144 KB per token

Source

Quantized byTeichAI
FamilyDeepSeek
Licenseapache-2.0
Downloads (HF)725
Last updated2025-12-07

Frequently asked questions about Qwen3 4B Thinking 2507 DeepSeek v3.2 Speciale Math Distill

How much VRAM does Qwen3 4B Thinking 2507 DeepSeek v3.2 Speciale Math Distill need?

About 4.2 GB at Q4_K_M with an 8K context window. That is the 2.5 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 4B Thinking 2507 DeepSeek v3.2 Speciale Math Distill on an 8 GB GPU?

Yes, with Q8_0: the 4.3 GB file needs about 6.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Qwen3 4B Thinking 2507 DeepSeek v3.2 Speciale Math Distill GGUF?

It depends on the quant: Q3_K_S is 1.9 GB, Q3_K_M is 2.1 GB, IQ4_NL is 2.4 GB, Q4_K_M is 2.5 GB, Q8_0 is 4.3 GB, Q8_0 is 4.3 GB and 2 more.

What context length does Qwen3 4B Thinking 2507 DeepSeek v3.2 Speciale Math Distill support?

The GGUF header lists a trained context length of 262,144 tokens (256K). 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 Qwen3 4B Thinking 2507 DeepSeek v3.2 Speciale Math Distill GGUF?

The files are on Hugging Face in the TeichAI/Qwen3-4B-Thinking-2507-DeepSeek-v3.2-Speciale-Math-Distill-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 4B Thinking 2507 DeepSeek v3.2 Speciale Math 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?

Yes, using Q3_K_S or Q3_K_M quantizations, which estimate 3.6–3.8 GB memory at 8k context.

Does the model support image input?

No, the model is text‑only and does not include vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Similar models

Browse all →

More from TeichAI

All by TeichAI →

More DeepSeek models

All DeepSeek →

Other small models

All small models →