QW

Qwen3.5 21B Claude 4.6 Opus Thinking EXP

QwenGGUF by mradermacherUpdated 2026-04-22
Download on Hugging Face
Parameters20.8B
Context256K
Layers48
Architectureqwen35
Smallest quant0.0 GB
Quick answer

Qwen3.5 21B Claude 4.6 Opus Thinking EXP needs about 15.0 GB of memory at Q4_K_M (a 12.8 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 24 quants, from 0.0 GB to 17.1 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

Qwen3.5 21B Claude 4.6 Opus Thinking EXP – a 20.8B parameter model

Qwen3.5 21B Claude 4.6 Opus Thinking EXP is a 20.8B parameter model from the Qwen family. It supports reasoning, roleplay, and tools. The model is released under the apache-2.0 license.

Good at

  • Reasoning
  • Roleplay
  • Tools

Limits

  • Large context size of 262144 tokens
  • No vision support
  • Requires high VRAM for larger quants

Best for

  • Complex reasoning tasks
  • Interactive roleplay scenarios
  • Tool‑enabled workflows

Who it’s for. Developers and researchers needing a large language model with strong reasoning and roleplay capabilities. The model is suitable for applications that can accommodate its memory requirements.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 2.1 GB
Fits Get file →
IQ1_S5.0 GB 7.1 GB
Fits Get file →
IQ1_M5.4 GB 7.5 GB
Tight Get file →
IQ2_XXS6.1 GB 8.2 GB
Too big Get file →
IQ2_XS6.6 GB 8.7 GB
Too big Get file →
IQ2_S6.9 GB 9.0 GB
Too big Get file →
IQ2_M7.4 GB 9.5 GB
Too big Get file →
Q2_K_S7.6 GB 9.7 GB
Too big Get file →
Q2_K8.0 GB 10.1 GB
Too big Get file →
IQ3_XXS8.4 GB 10.5 GB
Too big Get file →
IQ3_XS9.1 GB 11.2 GB
Too big Get file →
Q3_K_S9.5 GB 11.6 GB
Too big Get file →
IQ3_S9.5 GB 11.6 GB
Too big Get file →
IQ3_M9.8 GB 11.9 GB
Too big Get file →
Q3_K_M10.4 GB 12.5 GB
Too big Get file →
Q3_K_L10.9 GB 13.0 GB
Too big Get file →
IQ4_XS11.4 GB 13.6 GB
Too big Get file →
Q4_012.1 GB 14.2 GB
Too big Get file →
Q4_K_S12.1 GB 14.2 GB
Too big Get file →
Q4_K_M12.8 GB 15.0 GB
Too big Get file →
Q4_113.3 GB 15.4 GB
Too big Get file →
Q5_K_S14.5 GB 16.6 GB
Too big Get file →
Q5_K_M15.0 GB 17.1 GB
Too big Get file →
Q6_K17.1 GB 19.2 GB
Too big Get file →

For 8‑GB VRAM, use IQ1_S (file size 4.99 GB, memory 7.1 GB). For 12‑GB VRAM, IQ2_XS (6.63 GB, 8.7 GB) or Q2_K (7.96 GB, 10.1 GB). For 16‑GB VRAM, Q4_K_M (12.85 GB, 15 GB) or Q5_K_S (14.49 GB, 16.6 GB). Estimates are approximate.

What GPU do you need for Qwen3.5 21B Claude 4.6 Opus Thinking EXP?

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 2.1 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.1 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ1_M (5.4 GB file, about 7.5 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ3_M (9.8 GB file, about 11.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_1 (13.3 GB file, about 15.4 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (17.1 GB file, about 19.2 GB in use).

Which Qwen3.5 21B Claude 4.6 Opus Thinking EXP quant should you choose?

Q4_K_M is the usual starting point for Qwen3.5 21B Claude 4.6 Opus Thinking EXP: it balances file size and quality well. Here it is a 12.8 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

Architectureqwen35
Parameters20.8B
Layers48
Trained context262,144 tokens
KV cache (fp16)192 KB per token

Source

Quantized bymradermacher
FamilyQwen
Licenseapache-2.0
Downloads (HF)1,326
Last updated2026-04-22

Frequently asked questions about Qwen3.5 21B Claude 4.6 Opus Thinking EXP

How much VRAM does Qwen3.5 21B Claude 4.6 Opus Thinking EXP need?

About 15.0 GB at Q4_K_M with an 8K context window. That is the 12.8 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 Qwen3.5 21B Claude 4.6 Opus Thinking EXP on an 8 GB GPU?

Yes, with IQ1_M: the 5.4 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Qwen3.5 21B Claude 4.6 Opus Thinking EXP GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 5.0 GB, IQ1_M is 5.4 GB, IQ2_XXS is 6.1 GB, IQ2_XS is 6.6 GB, IQ2_S is 6.9 GB and 18 more.

What context length does Qwen3.5 21B Claude 4.6 Opus Thinking EXP support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.

Where can I download Qwen3.5 21B Claude 4.6 Opus Thinking EXP GGUF?

The files are on Hugging Face in the mradermacher/Qwen3.5-21B-Claude-4.6-Opus-Thinking-EXP-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 Qwen3.5 21B Claude 4.6 Opus Thinking EXP 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 IQ1_S which requires about 7.1 GB of VRAM at 8k context.

Does this model support vision?

No, the model does not have vision capabilities.

What license applies to this model?

The model is released under the apache-2.0 license.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Qwen models

All Qwen →

Other medium models

All medium models →