QW

Whittle Next Q4Exp

QwenGGUF by logic65Updated 2026-10-03
Download on Hugging Face
Parameters19.8B
Context256K
Layers32
Architectureqwen4exp
Smallest quant10.4 GB
Quick answer

Whittle Next Q4Exp needs about 12.0 GB of memory at Q4_K_M (a 10.4 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 5 quants, from 10.4 GB (Q4_K_M) to 39.6 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Whittle Next Q4Exp – 19.8B Qwen4exp model in GGUF format

Whittle Next Q4Exp is a 19.8B parameter Qwen4exp architecture model. It supports embedding, reasoning, and tools. The model is a research preview built by weight surgery on Whittle-tri-14.7B and released under Apache-2.0.

Good at

  • Embedding tasks
  • Reasoning queries
  • Tool invocation

Limits

  • No vision support
  • Requires large VRAM for full context
  • Research artifact, not production ready

Best for

  • Prototype LLM research
  • Embedding generation
  • Tool‑enabled workflows

Who it’s for. Developers and researchers who need a Qwen4exp model for experimentation. The model is suitable for those who can handle its memory requirements and are comfortable with a research‑grade artifact.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M10.4 GB 12.0 GB
Too big Get file →
Q4_K_M13.2 GB 14.8 GB
Too big Get file →
Q4_K_M13.2 GB 14.8 GB
Too big Get file →
Q4_K_M13.2 GB 14.8 GB
Too big Get file →
F1639.6 GB 41.2 GB
Too big Get file →

For 8‑GB VRAM, use the Q4_K_M quant with file size 10.4 GB; estimated memory at 8k context is 12 GB. For 12‑GB VRAM, the 13.2 GB Q4_K_M file uses about 14.8 GB memory. The F16 quant requires 39.64 GB file size and 41.2 GB memory, suitable only for high‑end GPUs.

What GPU do you need for Whittle Next Q4Exp?

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: the best quant that fits is Q4_K_M (10.4 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_M (13.2 GB file, about 14.8 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (13.2 GB file, about 14.8 GB in use).
  • 32 GB VRAM: the best quant that fits is Q4_K_M (13.2 GB file, about 14.8 GB in use).
  • 48 GB VRAM: the best quant that fits is F16 (39.6 GB file, about 41.2 GB in use).

Which Whittle Next Q4Exp quant should you choose?

Q4_K_M is the usual starting point for Whittle Next Q4Exp: it balances file size and quality well. Here it is a 10.4 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen4exp
Parameters19.8B (approximate, mixture of experts)
Layers32
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized bylogic65
FamilyQwen
Licenseapache-2.0
Downloads (HF)390
Last updated2026-10-03

Frequently asked questions about Whittle Next Q4Exp

How much VRAM does Whittle Next Q4Exp need?

About 12.0 GB at Q4_K_M with an 8K context window. That is the 10.4 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 Next Q4Exp on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Whittle Next Q4Exp GGUF?

It depends on the quant: Q4_K_M is 10.4 GB, Q4_K_M is 13.2 GB, Q4_K_M is 13.2 GB, Q4_K_M is 13.2 GB, F16 is 39.6 GB.

What context length does Whittle Next Q4Exp support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Whittle Next Q4Exp GGUF?

The files are on Hugging Face in the logic65/whittle-next 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 Next Q4Exp 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 Whittle Next Q4Exp on 8 GB VRAM?

The 10.4 GB Q4_K_M quant estimates 12 GB memory at 8k context, so 8 GB VRAM is insufficient.

What license does this model use?

Apache-2.0.

Does this model support vision?

No, it has no vision capabilities.

Other GGUFs of Qwen3.8-Whittle-tri-14.7B

Similar models

Browse all →

More from logic65

All by logic65 →

More Qwen models

All Qwen →

Other medium models

All medium models →