You can deploy this model and start earning money today!

Simplepotat/
Qwen3.8-27B-IQ5_KS-GGUF

Name: Qwen3.8-27B-IQ5_KS-GGUF
Availability: InStock

Views

No views yet

Qwen3.8-27B-IQ5_KS-GGUF

MTP capable and smaller non MTP IQ5_KS quants of Qwen 3.8 27B for use with ik_llama.cpp, created through reuse of Ubergarm's tensor recipe for Qwen 3.6 27B with his updated Qwen 3.8 imatrix.

Creation of this was possible due to the more or less identical structure of 3.8, and if the recipe is equally effective this should maintain SOTA performance for full 24GB offload.

Files

File	Purpose	Size	SHA-256
`Qwen3.8-27B-MTP-IQ5_KS.gguf`	MTP-capable build	18.963 GiB	`F879626127706403EF9B75C8E3F5E48D78B89FAD32D07A59127F2AFDD485C067`
`Qwen3.8-27B-no-MTP-IQ5_KS.gguf`	Smaller build with the MTP tensors removed	18.543 GiB	`07A86EDD155B9CB1321BBF65FB36D47B5856AE148C1869EB33A89895308D5F62`

The no-MTP file is 430.413 MiB smaller. With MTP disabled, the tested ik_llama.cpp loader ignores the embedded predictor tensors, so both files use the same VRAM but 430MiB less disk usage is 430MiB less disk usage.

MTP usage

bash

./llama-cli \
  -m Qwen3.8-27B-MTP-IQ5_KS.gguf \
  -ngl 999 \
  --spec-type mtp:n_max=1,p_min=0.0

Chat Template

Both GGUFs contain an exact match of the latest official Qwen3.8-27B chat template at the time of publication.

Sources and tooling

BF16 GGUF Source: ggml-org/Qwen3.8-27B-GGUF
Tensor Recipe: ubergarm/Qwen3.6-27B-GGUF
Importance Matrix: ubergarm/Qwen3.8-27B-GGUF
Individual-tensor quantizer: Thireus/ik_llama.cpp build 5263

Simplepotat/Qwen3.8-27B-IQ5_KS-GGUF