KI

Kiwen1.1 27B

KiwenGGUF by NikiKrutanUpdated 2026-09-21
Download on Hugging Face
Parameters27.3B
Context256K
Layers65
Architectureqwen35
Smallest quant8.9 GB
Quick answer

Kiwen1.1 27B needs about 17.4 GB of memory at IQ4_XS (a 14.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 15 quants, from 8.9 GB (IQ2_S) to 24.1 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 8.7 GB.

Kiwen1.1 27B – a 27‑billion‑parameter model focused on reasoning and coding

Kiwen1.1 27B is a fine‑tuned version of Qwen3.8‑27B. It emphasizes long chain‑of‑thought reasoning, coding, tool use, and instruction following. The model is released under Apache‑2.0 and supports vision tasks.

Good at

  • Long‑form reasoning
  • Coding and tool use
  • Instruction following

Limits

  • Large context requires high VRAM
  • No dedicated vision support beyond basic detection
  • Requires 8‑k context for memory estimates

Best for

  • Complex problem solving
  • Developing agent workflows
  • Educational tutoring

Who it’s for. Engineers and researchers who need a 27‑billion‑parameter model with strong reasoning and coding capabilities. The model is suitable for developers building agentic applications and educators creating interactive learning tools.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_S8.9 GB 11.6 GB
Too big Get file →
IQ2_S9.5 GB 12.2 GB
Too big Get file →
IQ2_S10.3 GB 13.0 GB
Too big Get file →
IQ3_XXS11.0 GB 13.7 GB
Too big Get file →
IQ3_S11.8 GB 14.5 GB
Too big Get file →
IQ3_S12.7 GB 15.4 GB
Too big Get file →
IQ4_XS13.6 GB 16.3 GB
Too big Get file →
IQ4_XS14.7 GB 17.4 GB
Too big Get file →
IQ4_XS15.7 GB 18.4 GB
Too big Get file →
Q5_K_M16.9 GB 19.6 GB
Too big Get file →
Q5_K_M18.1 GB 20.8 GB
Too big Get file →
Q5_K_M19.5 GB 22.2 GB
Too big Get file →
Q6_K21.0 GB 23.7 GB
Too big Get file →
Q6_K22.4 GB 25.1 GB
Too big Get file →
Q6_K24.1 GB 26.8 GB
Too big Get file →

For 8‑GB VRAM use IQ2_S (file size 8.91 GB, ~11.6 GB memory). For 16‑GB VRAM use IQ4_XS (file size 13.63 GB, ~16.3 GB memory). For 32‑GB VRAM use Q6_K (file size 20.97 GB, ~23.7 GB memory). Estimates are approximate.

What GPU do you need for Kiwen1.1 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: 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 IQ2_S (8.9 GB file, about 11.6 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_S (12.7 GB file, about 15.4 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (21.0 GB file, about 23.7 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (24.1 GB file, about 26.8 GB in use).

Which Kiwen1.1 27B quant should you choose?

IQ4_XS (14.7 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is IQ2_S at 8.9 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

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 byNikiKrutan
FamilyKiwen
Licenseapache-2.0
Downloads (HF)3,571
Last updated2026-09-21

Frequently asked questions about Kiwen1.1 27B

How much VRAM does Kiwen1.1 27B need?

About 17.4 GB at IQ4_XS with an 8K context window. That is the 14.7 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 Kiwen1.1 27B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Kiwen1.1 27B GGUF?

It depends on the quant: IQ2_S is 8.9 GB, IQ2_S is 9.5 GB, IQ2_S is 10.3 GB, IQ3_XXS is 11.0 GB, IQ3_S is 11.8 GB, IQ3_S is 12.7 GB and 9 more.

What context length does Kiwen1.1 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 Kiwen1.1 27B GGUF?

The files are on Hugging Face in the NikiKrutan/Kiwen1.1-27B-MTP-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 Kiwen1.1 27B 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 Kiwen1.1 27B on 8 GB VRAM?

Use the IQ2_S quant; it requires about 11.6 GB of VRAM at 8‑k context, which is close to 8 GB but may need swapping.

Does Kiwen1.1 27B support vision tasks?

The model has detected vision abilities, but it does not include dedicated vision modules; basic image prompts are supported.

What license applies to Kiwen1.1 27B?

The model is released under the Apache‑2.0 license.

Other GGUFs of Kiwen1.1-27B

Similar models

Browse all →

More from NikiKrutan

All by NikiKrutan →

More Kiwen models

All Kiwen →

Other medium models

All medium models →