Shadowgraph
TrendingAbout
Sign in
← Explore by area/Quantized LLM Model Deployment

Cluster 647073

30 repos

quantized ·1,984
4-bit ·1,944
conversational ·1,932
apple-silicon ·1,908
safetensors ·1,483
zh ·1,477
en ·1,477
8-bit ·1,432
multimodal ·1,430
qwen3_5 ·1,426

Related clusters

Quantized LLM Model Optimization39Qwen Model Quantization & Optimization15Quantized LLM Model Variants13Apple Silicon LLM Quantization9Quantized Qwen Language Models19Quantized MLX Model Deployments6

Reza2kn/Lance-3B-und-MLX-NVFP4

Model

Lance LLM (understanding path) — MLX 4-bit

0

2 commits

Reza2kn/Lance-3B-Video-und-MLX-NVFP4

Model

Lance LLM (understanding path) — MLX 4-bit

0

2 commits

Reza2kn/Lance-3B-und-MLX-4bit

Model

Lance LLM (understanding path) — MLX 4-bit

0

2 commits

Reza2kn/Lance-3B-Video-und-MLX-4bit

Model

Lance LLM (understanding path) — MLX 4-bit

0

2 commits

Reza2kn/Lance-3B-Video-und-MLX-4bit-DWQ

Model

Lance LLM (understanding path) — MLX 4-bit

0

2 commits

Reza2kn/Lance-3B-und-MLX-4bit-DWQ

Model

Lance LLM (understanding path) — MLX 4-bit

0

2 commits

Reza2kn/Lance-3B-Video-und-CoreML-palettized-4bit

Model

Lance LLM (understanding path) — 4-bit kmeans palettized (CoreML-ready)

0

2 commits

Reza2kn/Lance-3B-und-CoreML-palettized-4bit

Model

Lance LLM (understanding path) — 4-bit kmeans palettized (CoreML-ready)

0

2 commits

mlx-community/Lance-3B-AWQ-INT4

Model

Lance-3B-AWQ-INT4

0

3 commits

mlx-community/LongCat-Video-Avatar-1.5-q4-dmd-merged

Model

Part of the [LongCat-Video-Avatar 1.5 — MLX](https://huggingface.co/collections/mlx-community/longc…

2

3 commits

orcarouter/Qwen3.8-27B-Uncensored-MLX

Model

> An abliterated (refusal-removed) build of

1,416

1 commits

Reza2kn/Lance-3B-AWQ-INT4

Model

Lance-3B AWQ INT4 (image checkpoint)

0

2 commits

Reza2kn/Lance-3B-Video-AWQ-INT4

Model

Lance-3B-Video AWQ INT4

1

2 commits

Reza2kn/Lance-3B-NVFP4

Model

Lance-3B NVFP4 (image checkpoint)

1

2 commits

mlx-community/Laguna-S-2.1-oQ4e

Model

Laguna-S-2.1-oQ4e

10

18 commits

Reza2kn/Lance-3B-Video-NVFP4

Model

Lance-3B-Video NVFP4 (E2M1 + FP8 block scales)

2

2 commits

malaiwah/Qwen3.8-27B-K4

Model

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

0

52 commits

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

Model

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

2

62 commits

antirez/deepseek-v4-gguf

Model

DeepSeek V4 Flash — GGUF for ds4

473

28 commits

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

6 commits

OpenMOSS-Team/MOSS-VL-Instruct-0708-NF4

Model

English | 中文

15

5 commits

OpenMOSS-Team/MOSS-VL-Realtime-NF4

Model

English | 中文

14

7 commits

pearsonkyle/Qwen3.8-27B-GPTQ-W4A16

Model

🚀 Quick start

7

36 commits

matbee/kimodo-llm2vec-nf4

Model

matbee/kimodo-llm2vec-nf4

0

4 commits

mlx-community/Lance-3B-8bit

Model

> ⚠️ **SUPERSEDED — DO NOT USE.** This 8-bit checkpoint produces visibly degraded t2i

3

4 commits

ukint-vs/Nanbeige4.2-3B-CoreAI

Model

Nanbeige4.2-3B — Core AI INT8

1

5 commits

StephanST/C-radiov4_quantized

Model

C-RADIOv4 Quantized MLX Bundles

0

29 commits

aydin99/FLUX.2-klein-4B-int8

Model

FLUX.2-klein-4B Int8 Quantized

13

7 commits

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

8 commits

legraphista/glm-4-9b-chat-GGUF

Model

glm-4-9b-chat-GGUF

23

33 commits