QW

DEV ThinkingCap Qwen3.8 27B

QwenGGUF by ngquocvinhUpdated 2026-10-01
Download on Hugging Face
Parameters27.3B
Context256K
Layers65
Architectureqwen35
Smallest quant0.0 GB
Quick answer

DEV ThinkingCap Qwen3.8 27B needs about 19.5 GB of memory at Q4_K_M (a 16.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 20 quants, from 0.0 GB to 29.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.7 GB.

27B dense vision‑language model with 262,144 token context

DEV ThinkingCap Qwen3.8 27B is a community GGUF quantization of BottleCap AI’s 27B dense vision‑language model. It supports reasoning and vision tasks and offers a native context length of 262,144 tokens. The GGUF files range from 0.01 GB to 29.05 GB, covering a wide spectrum of memory footprints.

Good at

  • Large context reasoning
  • Vision‑language understanding
  • Text generation

Limits

  • Image input unverified with llama.cpp
  • No official training or fine‑tuning
  • License is other

Best for

  • Long‑form document analysis
  • Multimodal content creation
  • Research prototyping

Who it’s for. Developers and researchers who need a large vision‑language model in GGUF format. The model is suitable for experimentation and prototyping when a full‑fledged fine‑tuned version is not required.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 2.7 GB
Fits Get file →
Q1_04.7 GB 7.4 GB
Tight Get file →
IQ1_M7.9 GB 10.6 GB
Too big Get file →
IQ2_XS9.3 GB 12.0 GB
Too big Get file →
Q2_K_S10.5 GB 13.2 GB
Too big Get file →
Q2_K10.9 GB 13.5 GB
Too big Get file →
IQ3_XS12.2 GB 14.9 GB
Too big Get file →
Q3_K_S12.3 GB 14.9 GB
Too big Get file →
IQ3_S12.7 GB 15.3 GB
Too big Get file →
IQ3_M12.8 GB 15.5 GB
Too big Get file →
Q3_K_M13.5 GB 16.2 GB
Too big Get file →
Q3_K_L14.6 GB 17.2 GB
Too big Get file →
IQ4_XS15.3 GB 18.0 GB
Too big Get file →
Q4_K_S15.8 GB 18.5 GB
Too big Get file →
IQ4_NL16.0 GB 18.7 GB
Too big Get file →
Q4_K_M16.8 GB 19.5 GB
Too big Get file →
Q5_K_S19.0 GB 21.7 GB
Too big Get file →
Q5_K_M19.5 GB 22.2 GB
Too big Get file →
Q6_K22.4 GB 25.1 GB
Too big Get file →
Q8_029.0 GB 31.7 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (16.81 GB file, ~19.5 GB memory at 8k context). For 12 GB VRAM, Q3_K_M (13.5 GB file, ~16.2 GB memory). For 16 GB VRAM, Q2_K (10.86 GB file, ~13.5 GB memory). Memory estimates are approximate.

What GPU do you need for DEV ThinkingCap Qwen3.8 27B?

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 2.7 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
  • 8 GB VRAM: the best quant that fits is Q1_0 (4.7 GB file, about 7.4 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ2_XS (9.3 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_M (12.8 GB file, about 15.5 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_M (19.5 GB file, about 22.2 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (29.0 GB file, about 31.7 GB in use).

Which DEV ThinkingCap Qwen3.8 27B quant should you choose?

Q4_K_M is the usual starting point for DEV ThinkingCap Qwen3.8 27B: it balances file size and quality well. Here it is a 16.8 GB file.

The Q8_0 file is 29.0 GB, about 1.7 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 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
Parameters27.3B
Layers65
Trained context262,144 tokens
KV cache (fp16)260 KB per token

Source

Quantized byngquocvinh
FamilyQwen
Licenseother
Downloads (HF)7,609
Last updated2026-10-01

Frequently asked questions about DEV ThinkingCap Qwen3.8 27B

How much VRAM does DEV ThinkingCap Qwen3.8 27B need?

About 19.5 GB at Q4_K_M with an 8K context window. That is the 16.8 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 DEV ThinkingCap Qwen3.8 27B on an 8 GB GPU?

Yes, with Q1_0: the 4.7 GB file needs about 7.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of DEV ThinkingCap Qwen3.8 27B GGUF?

It depends on the quant: file is 0.0 GB, Q1_0 is 4.7 GB, IQ1_M is 7.9 GB, IQ2_XS is 9.3 GB, Q2_K_S is 10.5 GB, Q2_K is 10.9 GB and 14 more.

What context length does DEV ThinkingCap Qwen3.8 27B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.2 GB at 8K and 8.7 GB at 32K.

Where can I download DEV ThinkingCap Qwen3.8 27B GGUF?

The files are on Hugging Face in the ngquocvinh/ThinkingCap-Qwen3.8-27B-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 DEV ThinkingCap Qwen3.8 27B use?

Hugging Face lists the license as other. 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 the Q4_K_M quantization; it requires about 19.5 GB memory at 8k context, so 8 GB VRAM is insufficient.

Is image input supported?

Image input is unverified with the current llama.cpp build; token decoding fails for images.

Does this model have official training?

No, it is a community GGUF quantization without additional training or fine‑tuning.

Other GGUFs of ThinkingCap-Qwen3.8-27B

Similar models

Browse all →

More from ngquocvinh

All by ngquocvinh →

More Qwen models

All Qwen →

Other medium models

All medium models →