Shadowgraph
TrendingAbout
Sign in

Jundot/Qwen3.8-27B-oQ4e-fp16-mtp

Model

Qwen3.8-27B-oQ4e-fp16-mtp

8

2 commits

2 linked in READMEs

updated Aug 18, 2026

See the code
4-bit
oq
quantized
qwen3_5
safetensors

README

Qwen3.8-27B-oQ4e-fp16-mtp

This model was quantized using oQ (oMLX v0.6.1) mixed-precision quantization.

Quantization details

  • Model type: qwen3_5
  • Bits: 4
  • Group size: 64
  • Format: MLX safetensors

Contributors

Jundot

2 commits

Similar repos

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

Model

Qwen3.8-Flash-Next-AWQ-W4A16

29

AutomatosX/AX-Qwen3.8-27B-MLX-AXQ-4bit-MTP

Model

AX-Qwen3.8-27B-MLX-AXQ-4bit-MTP

4

AutomatosX/AX-Qwen3.8-27B-MLX-AXQ-MXFP4-MTP

Model

AX-Qwen3.8-27B-MLX-AXQ-MXFP4-MTP — 4.84 BPW measured main

0

AutomatosX/AX-Qwen3.8-27B-MLX-AXQ-8bit-MTP

Model

AX-Qwen3.8-27B-MLX-AXQ-8bit-MTP — 8.63 BPW measured main

0

AutomatosX/AX-Qwen3.8-27B-MLX-AXQ-4bit

Model

AX-Qwen3.8-27B-MLX-AXQ-4bit

1

AutomatosX/AX-Qwen3-Embedding-4B-MLX-AXQ-8bit

Model

AX-Qwen3-Embedding-4B-MLX-AXQ-8bit

0

AutomatosX/AX-Qwen3-Embedding-8B-MLX-AXQ-4bit

Model

AX-Qwen3-Embedding-8B-MLX-AXQ-4bit

0

AutomatosX/AX-Holo-3.1-35B-A3B-MLX-AXQ-8bit

Model

AX-Holo-3.1-35B-A3B-MLX-AXQ-8bit — 9.42 BPW measured main

0

Linked in READMEs

jundot/omlx

LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the…

21,885

README badge

cr0sh/qw

QW (QuasarWave) is a highly opinionated LLM inference runtime targeting MLX-only, single-user…

3

README badge

Jundot/Qwen3.8-27B-oQ4e-fp16-mtp

Model

Qwen3.8-27B-oQ4e-fp16-mtp

8

2 commits

2 linked in READMEs

updated Aug 18, 2026

See the code
4-bit
oq
quantized
qwen3_5
safetensors

README

Qwen3.8-27B-oQ4e-fp16-mtp

This model was quantized using oQ (oMLX v0.6.1) mixed-precision quantization.

Quantization details

  • Model type: qwen3_5
  • Bits: 4
  • Group size: 64
  • Format: MLX safetensors

Similar repos

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

Model

Qwen3.8-Flash-Next-AWQ-W4A16

29

AutomatosX/AX-Qwen3.8-27B-MLX-AXQ-4bit-MTP

Model

AX-Qwen3.8-27B-MLX-AXQ-4bit-MTP

4

AutomatosX/AX-Qwen3.8-27B-MLX-AXQ-MXFP4-MTP

Model

AX-Qwen3.8-27B-MLX-AXQ-MXFP4-MTP — 4.84 BPW measured main

0

AutomatosX/AX-Qwen3.8-27B-MLX-AXQ-8bit-MTP

Model

AX-Qwen3.8-27B-MLX-AXQ-8bit-MTP — 8.63 BPW measured main

0

AutomatosX/AX-Qwen3.8-27B-MLX-AXQ-4bit

Model

AX-Qwen3.8-27B-MLX-AXQ-4bit

1

AutomatosX/AX-Qwen3-Embedding-4B-MLX-AXQ-8bit

Model

AX-Qwen3-Embedding-4B-MLX-AXQ-8bit

0

AutomatosX/AX-Qwen3-Embedding-8B-MLX-AXQ-4bit

Model

AX-Qwen3-Embedding-8B-MLX-AXQ-4bit

0

AutomatosX/AX-Holo-3.1-35B-A3B-MLX-AXQ-8bit

Model

AX-Holo-3.1-35B-A3B-MLX-AXQ-8bit — 9.42 BPW measured main

0

Linked in READMEs

jundot/omlx

LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the…

21,885

README badge

cr0sh/qw

QW (QuasarWave) is a highly opinionated LLM inference runtime targeting MLX-only, single-user…

3

README badge

Contributors

Jundot

2 commits