QW

Qwen3 Esper3 Reasoning CODER Instruct 21B Brainstorm20x

QwenGGUF by mradermacherUpdated 2025-12-18
Download on Hugging Face
Parameters21B
Context40K
Layers59
Architectureqwen3
Smallest quant0.0 GB
Quick answer

Qwen3 Esper3 Reasoning CODER Instruct 21B Brainstorm20x needs about 15.2 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 17.3 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 7.9 GB.

Qwen3 21B model focused on coding and reasoning

Qwen3 Esper3 Reasoning CODER Instruct 21B Brainstorm20x is a 21‑billion‑parameter LLM. It excels at code generation and logical reasoning tasks. The model is released under the apache‑2.0 license and supports a 40960‑token context window.

Good at

  • Code generation
  • Logical reasoning
  • Instruction following

Limits

  • No vision support
  • Large VRAM requirement for higher quants
  • Limited to 40960 context tokens

Best for

  • Developers needing code assistance
  • Researchers working on reasoning tasks
  • Educators creating coding exercises

Who it’s for. This model is ideal for users who need robust coding support and advanced reasoning capabilities. It is suitable for developers, researchers, and educators who can allocate sufficient GPU memory for the desired quantization level.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 2.5 GB
Fits Get file →
IQ1_S4.9 GB 7.4 GB
Tight Get file →
IQ1_M5.3 GB 7.8 GB
Tight Get file →
IQ2_XXS6.0 GB 8.4 GB
Too big Get file →
IQ2_XS6.5 GB 9.0 GB
Too big Get file →
IQ2_S6.9 GB 9.4 GB
Too big Get file →
IQ2_M7.4 GB 9.9 GB
Too big Get file →
Q2_K_S7.5 GB 10.0 GB
Too big Get file →
Q2_K8.1 GB 10.5 GB
Too big Get file →
IQ3_XXS8.3 GB 10.8 GB
Too big Get file →
IQ3_XS8.9 GB 11.4 GB
Too big Get file →
Q3_K_S9.4 GB 11.8 GB
Too big Get file →
IQ3_S9.4 GB 11.9 GB
Too big Get file →
IQ3_M9.7 GB 12.2 GB
Too big Get file →
Q3_K_M10.3 GB 12.8 GB
Too big Get file →
Q3_K_L11.2 GB 13.7 GB
Too big Get file →
IQ4_XS11.5 GB 13.9 GB
Too big Get file →
Q4_012.1 GB 14.6 GB
Too big Get file →
Q4_K_S12.1 GB 14.6 GB
Too big Get file →
Q4_K_M12.8 GB 15.2 GB
Too big Get file →
Q4_113.3 GB 15.8 GB
Too big Get file →
Q5_K_S14.6 GB 17.1 GB
Too big Get file →
Q5_K_M14.9 GB 17.4 GB
Too big Get file →
Q6_K17.3 GB 19.8 GB
Too big Get file →

For 8‑GB VRAM, use IQ1_S (7.4 GB) or IQ1_M (7.8 GB). With 12‑GB VRAM, Q4_0 (14.6 GB) or Q4_K_S (14.6 GB) are suitable. For 16‑GB VRAM, Q4_K_M (15.2 GB) or Q5_K_S (17.1 GB) provide higher quality. Estimates are approximate.

What GPU do you need for Qwen3 Esper3 Reasoning CODER Instruct 21B Brainstorm20x?

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 2.5 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.5 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ1_M (5.3 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ3_S (9.4 GB file, about 11.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_1 (13.3 GB file, about 15.8 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (17.3 GB file, about 19.8 GB in use).

Which Qwen3 Esper3 Reasoning CODER Instruct 21B Brainstorm20x quant should you choose?

Q4_K_M is the usual starting point for Qwen3 Esper3 Reasoning CODER Instruct 21B Brainstorm20x: 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

Architectureqwen3
Parameters21B
Layers59
Trained context40,960 tokens
KV cache (fp16)236 KB per token

Source

Quantized bymradermacher
FamilyQwen
Licenseapache-2.0
Downloads (HF)1,464
Last updated2025-12-18

Frequently asked questions about Qwen3 Esper3 Reasoning CODER Instruct 21B Brainstorm20x

How much VRAM does Qwen3 Esper3 Reasoning CODER Instruct 21B Brainstorm20x need?

About 15.2 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 Esper3 Reasoning CODER Instruct 21B Brainstorm20x on an 8 GB GPU?

Yes, with IQ1_M: the 5.3 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Qwen3 Esper3 Reasoning CODER Instruct 21B Brainstorm20x GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 4.9 GB, IQ1_M is 5.3 GB, IQ2_XXS is 6.0 GB, IQ2_XS is 6.5 GB, IQ2_S is 6.9 GB and 18 more.

What context length does Qwen3 Esper3 Reasoning CODER Instruct 21B Brainstorm20x support?

The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 2.0 GB at 8K and 7.9 GB at 32K.

Where can I download Qwen3 Esper3 Reasoning CODER Instruct 21B Brainstorm20x GGUF?

The files are on Hugging Face in the mradermacher/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x-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 Esper3 Reasoning CODER Instruct 21B Brainstorm20x 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?

Use IQ1_S or IQ1_M quantizations, which estimate 7.4–7.8 GB memory at 8k context.

Does the model support vision tasks?

No, the model 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 mradermacher

All by mradermacher →

More Qwen models

All Qwen →

Other medium models

All medium models →