Shadowgraph
TrendingAbout
Sign in

turboderp/Qwen3.8-27B-exl3

Model

EXL3 quants of Qwen3.8-27B

130

13 commits

1 linked in READMEs

updated Aug 27, 2026

See the code
exl3

README

EXL3 quants of Qwen3.8-27B

Calibration trace: md JSON safetensors
Eval trace: md JSON

Self-calibrated quants:

Rightmost column are variants with quantized vision tower and require ExLlamaV3 v1.4.4 to work properly

1.40 bits per weight / H3 -- 1.40 bits per weight / H3 / V3
1.60 bits per weight / H3 -- 1.60 bits per weight / H3 / V3
1.80 bits per weight / H3 -- 1.80 bits per weight / H3 / V3
2.00 bits per weight / H3 -- 2.00 bits per weight / H3 / V3
2.20 bits per weight / H3 -- 2.20 bits per weight / H3 / V3
3.00 bits per weight / H4 -- 3.00 bits per weight / H4 / V4
4.00 bits per weight / H5 -- 4.00 bits per weight / H5 / V6
5.00 bits per weight / H6 -- 5.00 bits per weight / H6 / V6
6.00 bits per weight / H6 -- 6.00 bits per weight / H6 / V6

Plain quants:

2.00 bits per weight
2.50 bits per weight
3.00 bits per weight
3.50 bits per weight
4.00 bits per weight
5.00 bits per weight
6.00 bits per weight

qbsg_kld_vram qbsg_ppl_vram qbsg_kld_hist_combined

Contributors

turboderp

13 commits

Similar repos

Mia-AiLab/Qwen3.8-27B-EXL3-2.0bpw

Model

Qwen3.8-27B-EXL3 2.0bpw (Mirror)

0

malaiwah/Qwen3.8-27B-EXL3-K5K6

Model

> **Part of the [Qwen3.8-27B mixed-precision EXL3 (measured)](https://huggingface.co/collections/ma…

1

malaiwah/Qwen3.8-27B-K4

Model

> **Part of the [Qwen3.8-27B mixed-precision EXL3 (measured)](https://huggingface.co/collections/ma…

0

malaiwah/Qwen3.8-27B-EXL3-S16-V-research

Model

Research artifact, not a release: the first sub-4-bit build in this family, measured and rejected

0

malaiwah/Qwen3.8-27B-EXL3-K6-parity

Model

Near-equal file bytes: EXL3 measures 0.001634 and GGUF `Q6_K` 0.002035 on the same suite, with…

1

wtdcode/Qwen3.8-Flash-Next-AWQ-W4A16

Model

Qwen3.8-Flash-Next-AWQ-W4A16

28

Avesed/Qwen3.6-27B-INT8-W8A8

Model

Qwen3.6-27B-INT8-W8A8

5

caiovicentino1/Qwen3.5-9B-EOQ-v3

Model

🏆 EOQ v3 -- Qwen3.5-9B (PolarQuant + AWQ)

1

Linked in READMEs

MiaAI-Lab/Qwen3.8-27B-16gb-NVIDIA-GPUs-one-click-install

Qwen3.8-27B on 16-32 GB Nvidia GPUs one-click install for Windows / Linux

439

README badge

turboderp/Qwen3.8-27B-exl3

Model

EXL3 quants of Qwen3.8-27B

130

13 commits

1 linked in READMEs

updated Aug 27, 2026

See the code
exl3

README

EXL3 quants of Qwen3.8-27B

Calibration trace: md JSON safetensors
Eval trace: md JSON

Self-calibrated quants:

Rightmost column are variants with quantized vision tower and require ExLlamaV3 v1.4.4 to work properly

1.40 bits per weight / H3 -- 1.40 bits per weight / H3 / V3
1.60 bits per weight / H3 -- 1.60 bits per weight / H3 / V3
1.80 bits per weight / H3 -- 1.80 bits per weight / H3 / V3
2.00 bits per weight / H3 -- 2.00 bits per weight / H3 / V3
2.20 bits per weight / H3 -- 2.20 bits per weight / H3 / V3
3.00 bits per weight / H4 -- 3.00 bits per weight / H4 / V4
4.00 bits per weight / H5 -- 4.00 bits per weight / H5 / V6
5.00 bits per weight / H6 -- 5.00 bits per weight / H6 / V6
6.00 bits per weight / H6 -- 6.00 bits per weight / H6 / V6

Plain quants:

2.00 bits per weight
2.50 bits per weight
3.00 bits per weight
3.50 bits per weight
4.00 bits per weight
5.00 bits per weight
6.00 bits per weight

qbsg_kld_vram qbsg_ppl_vram qbsg_kld_hist_combined

Similar repos

Mia-AiLab/Qwen3.8-27B-EXL3-2.0bpw

Model

Qwen3.8-27B-EXL3 2.0bpw (Mirror)

0

malaiwah/Qwen3.8-27B-EXL3-K5K6

Model

> **Part of the [Qwen3.8-27B mixed-precision EXL3 (measured)](https://huggingface.co/collections/ma…

1

malaiwah/Qwen3.8-27B-K4

Model

> **Part of the [Qwen3.8-27B mixed-precision EXL3 (measured)](https://huggingface.co/collections/ma…

0

malaiwah/Qwen3.8-27B-EXL3-S16-V-research

Model

Research artifact, not a release: the first sub-4-bit build in this family, measured and rejected

0

malaiwah/Qwen3.8-27B-EXL3-K6-parity

Model

Near-equal file bytes: EXL3 measures 0.001634 and GGUF `Q6_K` 0.002035 on the same suite, with…

1

wtdcode/Qwen3.8-Flash-Next-AWQ-W4A16

Model

Qwen3.8-Flash-Next-AWQ-W4A16

28

Avesed/Qwen3.6-27B-INT8-W8A8

Model

Qwen3.6-27B-INT8-W8A8

5

caiovicentino1/Qwen3.5-9B-EOQ-v3

Model

🏆 EOQ v3 -- Qwen3.5-9B (PolarQuant + AWQ)

1

Linked in READMEs

MiaAI-Lab/Qwen3.8-27B-16gb-NVIDIA-GPUs-one-click-install

Qwen3.8-27B on 16-32 GB Nvidia GPUs one-click install for Windows / Linux

439

README badge

Contributors

turboderp

13 commits