Shadowgraph
TrendingAbout
Sign in
← Explore by area/Language Model Inference Optimization

Cluster 638877

39 repos

Python · 2
speculative-decoding ·1,791
safetensors ·1,770
text-generation ·1,748
transformers ·1,695
text-generation-inference ·1,690
qwen3 ·1,687
dflash ·1,442
diffusion-language-model ·1,364
efficiency ·1,364
qwen ·1,296

Related clusters

Qwen LLM Inference Optimization9LLM Quantization and ROCm Optimization38Medical LLMs and Healthcare AI11GGUF quantized language models36Cluster 63525931Cluster 63955813

z-lab/Qwen3-Coder-Next-DFlash

Model

Qwen3-Coder-Next-DFlash

15

12 commits

z-lab/gemma-4-26B-A4B-it-DFlash

Model

gemma-4-26B-A4B-it-DFlash

59

27 commits

z-lab/gemma-4-31B-it-DFlash

Model

gemma-4-31B-it-DFlash

111

19 commits

z-lab/Qwen3.5-27B-DFlash

Model

Qwen3.5-27B-DFlash

113

44 commits

z-lab/Qwen3.5-4B-DFlash

Model

Qwen3.5-4B-DFlash

40

42 commits

z-lab/Qwen3.5-9B-DFlash

Model

Qwen3.5-9B-DFlash

43

44 commits

z-lab/Qwen3.6-35B-A3B-DFlash

Model

Qwen3.6-35B-A3B-DFlash

295

33 commits

z-lab/Qwen3.5-122B-A10B-DFlash

Model

Qwen3.5-122B-A10B-DFlash

20

18 commits

z-lab/Qwen3.5-35B-A3B-DFlash

Model

Qwen3.5-35B-A3B-DFlash

45

34 commits

z-lab/MiniMax-M2.5-DFlash

Model

MiniMax-M2.5-DFlash

9

15 commits

z-lab/MiniMax-M2.7-DFlash

Model

No description

28

0 commits

z-lab/Qwen3-8B-DFlash-b16

Model

Qwen3-8B-DFlash-b16

29

25 commits

z-lab/Qwen3-4B-DFlash-b16

Model

Qwen3-4B-DFlash-b16

31

22 commits

z-lab/Qwen3-Coder-30B-A3B-DFlash

Model

Qwen3-Coder-30B-A3B-DFlash

35

35 commits

z-lab/Qwen3.6-27B-DFlash

Model

Qwen3.6-27B-DFlash

400

12 commits

Avesed/Qwen3.6-27B-DSpark

Model

Qwen3.6-27B DSpark draft head

6

8 commits

z-lab/LLaMA3.1-8B-Instruct-DFlash-UltraChat

Model

LLaMA3.1-8B-Instruct-DFlash-UltraChat

3

17 commits

z-lab/Kimi-K2.5-DFlash

Model

Kimi-K2.5-DFlash

33

47 commits

incoai/Qwen3.8-27B-DFlash2

Model

Qwen3.8-27B-DFlash2

236

2 commits

z-lab/gpt-oss-20b-DFlash

Model

gpt-oss-20b-DFlash

26

12 commits

z-lab/gpt-oss-120b-DFlash

Model

gpt-oss-120b-DFlash

10

11 commits

z-lab/Muse-Glimmer-30B-DFlash2

Model

Muse-Glimmer-30B-DFlash2

15

3 commits

z-lab/Kimi-K2.6-DFlash

Model

No description

19

0 commits

RadixArk/Inkling-DSpark-Preview

Model

Inkling DSpark speculator

3

14 commits

RadixArk/Kimi-K3-DSpark

Model

Kimi K3 DSpark speculator

56

6 commits

Lucebox/gemma-4-31B-it-DFlash-GGUF

Model

gemma-4-31B-it DFlash Draft — Q8_0 GGUF

7

3 commits

Lucebox/gemma-4-26B-A4B-it-DFlash-GGUF

Model

gemma-4-26B-A4B-it DFlash Draft — Q8_0 GGUF

2

3 commits

Zjcxy-SmartAI/Eagle3-Qwen3-8B-zh

Model

Eagle3-Qwen3-8B-zh

3

11 commits

lightseekorg/kimi-k3-dflash2

Model

Kimi-K3 DFlash2 draft

4

6 commits

DAWNCR0W/dflasher

CLI for building and testing DFlash-style speculative decoding draft models.

Python

0

6 commits

AdaFlash/Qwen3-8B-AdaFlash

Model

AdaFlash: Adaptive Speculative Decoding via On-Policy Distilled Diffusion Drafters

0

4 commits

RedHatAI/Qwen3-8B-speculator.peagle

Model

RedHatAI/Qwen3-8B-speculator.peagle

0

4 commits

thoughtworks/GLM-4.7-Flash-Eagle3

Model

EAGLE3 Draft Model for GLM-4.7-Flash

2

9 commits

Lucebox/Laguna-XS-2.1-DFlash-GGUF

Model

Laguna-XS-2.1-DFlash-GGUF (quantized drafter)

4

4 commits

lightseekorg/kimi-k2.5-eagle3

Model

Model Overview

15

6 commits

Inferact/MiniMax-M3-EAGLE3

Model

Model Overview

14

7 commits

Inferact/Kimi-K3-DSpark

Model

Model Overview

55

4 commits

47thtechcorner/RayCodes_Qwen_3.8_DFlash2

Qwen 3.8 DFlash2: 27B AI Running at 236 TOK/S Locally! - High-speed local prose and code…

Python

5

1 commits

mattbucci/Devstral-Small-2-24B-AWQ-EAGLE3

Model

Devstral-Small-2-24B-AWQ-EAGLE3

0

3 commits