TH

ThinkLess 2B

ThinklessGGUF by mradermacherUpdated 2026-10-02
Download on Hugging Face
Parameters1.94B
Context256K
Layers25
Architectureqwen35
Smallest quant1.0 GB
Quick answer

ThinkLess 2B needs about 2.2 GB of memory at Q4_K_M (a 1.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 1.0 GB (Q2_K) to 3.9 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.7 GB.

ThinkLess‑2B: a 1.94B‑parameter Qwen3.5 model optimized for efficient reasoning

ThinkLess‑2B is a 1.94B‑parameter Qwen3.5 model that reduces reasoning token usage while maintaining accuracy. It supports reasoning, tools, and vision. The model is released under Apache‑2.0.

Good at

  • Efficient reasoning with fewer tokens
  • Supports tools and vision
  • Fast inference with vLLM and MTP

Limits

  • No vision support beyond basic
  • Requires 8,192‑token context for full performance
  • No mixture‑of‑experts

Best for

  • Short‑form Q&A with token limits
  • Tool‑integrated workflows
  • Vision‑enabled inference on supported hardware

Who it’s for. Developers building applications that need quick, accurate answers with limited token budgets. Researchers testing efficient reasoning models. Teams deploying on GPUs with moderate VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.0 GB 1.9 GB
Fits Get file →
Q3_K_S1.0 GB 2.0 GB
Fits Get file →
Q3_K_M1.1 GB 2.0 GB
Fits Get file →
Q3_K_L1.2 GB 2.1 GB
Fits Get file →
IQ4_XS1.2 GB 2.2 GB
Fits Get file →
Q4_K_S1.2 GB 2.2 GB
Fits Get file →
Q4_K_M1.3 GB 2.2 GB
Fits Get file →
Q5_K_S1.4 GB 2.3 GB
Fits Get file →
Q5_K_M1.5 GB 2.4 GB
Fits Get file →
Q6_K1.6 GB 2.5 GB
Fits Get file →
Q8_02.1 GB 3.0 GB
Fits Get file →
F163.9 GB 4.8 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_S (file size 1.25 GB, estimated 2.2 GB memory). For 12 GB VRAM, Q5_K_M (1.45 GB, 2.4 GB memory) or Q6_K (1.61 GB, 2.5 GB memory). For 16 GB VRAM, Q8_0 (2.08 GB, 3 GB memory) or F16 (3.9 GB, 4.8 GB memory). Estimates are approximate.

What GPU do you need for ThinkLess 2B?

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 Q8_0 (2.1 GB file, about 3.0 GB in use).
  • 6 GB VRAM: the best quant that fits is F16 (3.9 GB file, about 4.8 GB in use).

Which ThinkLess 2B quant should you choose?

Q4_K_M is the usual starting point for ThinkLess 2B: it balances file size and quality well. Here it is a 1.3 GB file.

The Q8_0 file is 2.1 GB, about 1.6 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 Q2_K at 1.0 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters1.94B
Layers25
Trained context262,144 tokens
KV cache (fp16)50 KB per token

Source

Quantized bymradermacher
FamilyThinkless
Licenseapache-2.0
Downloads (HF)396
Last updated2026-10-02

Frequently asked questions about ThinkLess 2B

How much VRAM does ThinkLess 2B need?

About 2.2 GB at Q4_K_M with an 8K context window. That is the 1.3 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 ThinkLess 2B on an 8 GB GPU?

Yes, with F16: the 3.9 GB file needs about 4.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of ThinkLess 2B GGUF?

It depends on the quant: Q2_K is 1.0 GB, Q3_K_S is 1.0 GB, Q3_K_M is 1.1 GB, Q3_K_L is 1.2 GB, IQ4_XS is 1.2 GB, Q4_K_S is 1.2 GB and 6 more.

What context length does ThinkLess 2B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.7 GB at 32K.

Where can I download ThinkLess 2B GGUF?

The files are on Hugging Face in the mradermacher/ThinkLess-2B-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 ThinkLess 2B 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 ThinkLess‑2B on 8 GB VRAM?

Yes, the Q4_K_S quant uses about 2.2 GB memory at 8,192 context, fitting in 8 GB VRAM.

Does ThinkLess‑2B support vision?

Yes, the model has detected vision ability, but it requires appropriate hardware and libraries.

What license applies to ThinkLess‑2B?

The model is released under the Apache‑2.0 license.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Thinkless models

All Thinkless →

Other tiny models

All tiny models →