QW

Whittle Qwen 3.8 35B A3B

QwenGGUF by logic65Updated 2026-10-03
Download on Hugging Face
Parameters35.5B
Context256K
Layers40
Architectureqwen4exp
Smallest quant16.7 GB
Quick answer

Whittle Qwen 3.8 35B A3B needs about 22.5 GB of memory at Q4_K_M (a 21.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 5 quants, from 16.7 GB (Q3_K_M) to 37.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.

Whittle Qwen 3.8 35B A3B – a 35‑billion‑parameter, 3‑billion‑active mixture‑of‑experts model in Qwen4exp format

Whittle Qwen 3.8 35B A3B is a 35.1 B‑parameter, ~3 B‑active mixture‑of‑experts model built on the Qwen3.8‑Flash‑Next architecture. It is distilled from Qwen3.8‑27B and includes a 10 B‑parameter n‑gram memory that is load‑bearing. The model runs on stock llama.cpp with no patches.

Good at

  • Coding tasks
  • Reasoning problems
  • Long‑context handling

Limits

  • Requires large VRAM for full performance
  • Memory rows must be kept in system RAM
  • No vision support

Best for

  • Software development assistance
  • Complex problem solving
  • Extended conversation contexts

Who it’s for. Developers and researchers who need a large, long‑context language model for code generation and reasoning. The model is suitable for users with access to sufficient GPU and system memory resources.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M16.7 GB 17.9 GB
Too big Get file →
Q4_K_M21.3 GB 22.5 GB
Too big Get file →
Q5_K_M25.1 GB 26.3 GB
Too big Get file →
Q6_K29.3 GB 30.4 GB
Too big Get file →
Q8_037.8 GB 39.0 GB
Too big Get file →

For 8 GB VRAM, use Q3_K_M (file size 16.73 GB, ~17.9 GB RAM at 8k context). For 12 GB VRAM, Q4_K_M (21.28 GB, ~22.5 GB RAM). For 16 GB VRAM, Q5_K_M (25.13 GB, ~26.3 GB RAM). Higher quants provide better quality but need more memory.

What GPU do you need for Whittle Qwen 3.8 35B A3B?

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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is Q4_K_M (21.3 GB file, about 22.5 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (29.3 GB file, about 30.4 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (37.8 GB file, about 39.0 GB in use).

Which Whittle Qwen 3.8 35B A3B quant should you choose?

Q4_K_M is the usual starting point for Whittle Qwen 3.8 35B A3B: it balances file size and quality well. Here it is a 21.3 GB file.

The Q8_0 file is 37.8 GB, about 1.8 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_M at 16.7 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

Architectureqwen4exp
Parameters35.5B (approximate, mixture of experts)
Active parameters3B
Layers40
Trained context262,144 tokens
KV cache (fp16)80 KB per token

Source

Quantized bylogic65
FamilyQwen
Licenseapache-2.0
Downloads (HF)23,639
Last updated2026-10-03

Frequently asked questions about Whittle Qwen 3.8 35B A3B

How much VRAM does Whittle Qwen 3.8 35B A3B need?

About 22.5 GB at Q4_K_M with an 8K context window. That is the 21.3 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 Whittle Qwen 3.8 35B A3B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 17.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Whittle Qwen 3.8 35B A3B GGUF?

It depends on the quant: Q3_K_M is 16.7 GB, Q4_K_M is 21.3 GB, Q5_K_M is 25.1 GB, Q6_K is 29.3 GB, Q8_0 is 37.8 GB.

What context length does Whittle Qwen 3.8 35B A3B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.7 GB at 32K.

Where can I download Whittle Qwen 3.8 35B A3B GGUF?

The files are on Hugging Face in the logic65/Whittle-Qwen-3.8-35B-A3B-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 Whittle Qwen 3.8 35B A3B 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 the Q3_K_M quantization which requires about 17.9 GB of RAM at 8k context. It will run on 8 GB VRAM but needs additional system RAM.

Does this model support vision?

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 Whittle-Qwen-3.8-35B-A3B

Similar models

Browse all →

More from logic65

All by logic65 →

More Qwen models

All Qwen →

Other large models

All large models →