Hugging Face model family · zai-org
GLM-5.3-Flash model family
Trace GLM-5.3-Flash and its 644 community derivatives back to the base model. Model Dig maps the lineage of GGUF quantizations, merges, adapters and fine-tunes, ranked by download heat and likes — so you can see exactly how each variant relates to GLM-5.3-Flash.
Open interactive lineage graph → Browse all families
645 models in family
118 GGUF variants
6,363,073 base downloads
2026-08-25 base released
Popular GLM-5.3-Flash derivatives
| # | Model | Author | Downloads | Likes |
|---|---|---|---|---|
| 1 | GLM-5.3-Flash-Maya-GGUF GGUFFlash | peasantsmith | ⬇ 1,370,617 | ♥ 114 |
| 2 | GLM-5.3-Flash-GGUF GGUFFlash | unsloth | ⬇ 744,606 | ♥ 534 |
| 3 | glm-5.3-flash-exlr8-k2-k3-k4 Flash | kindlingai | ⬇ 397,431 | ♥ 4 |
| 4 | Hy4-preview-GGUF GGUF | AngelSlim | ⬇ 302,741 | ♥ 102 |
| 5 | GLM-5.3-Flash-CYBERSECURITY-GGUF GGUFCybersecurityFlashllama.cpp | SyndicateLabs | ⬇ 178,368 | ♥ 27 |
| 6 | GLM-5.3-Flash-NVFP4 NVFP4FlashSGLang | tattrongvu | ⬇ 86,941 | ♥ 1 |
| 7 | GLM-5.3-Flash-NVFP4 NVFP4Flash | nvidia | ⬇ 54,332 | ♥ 193 |
| 8 | GLM-5.3-Flash-NVFP4 NVFP4Flash | RadixArk | ⬇ 52,481 | ♥ 10 |
| 9 | GLM-5.3-Flash-REAP50-GGUF GGUFFlashllama.cpp | patrickbdevaney | ⬇ 51,905 | ♥ 25 |
| 10 | glm-5.3-flash-gguf GGUFFlash | antirez | ⬇ 49,629 | ♥ 40 |
| 11 | orcarouter_GLM-5.3-Flash-Uncensored-GGUF GGUFFlashUncensored | BoldingBuilds | ⬇ 47,441 | ♥ 45 |
| 12 | GLM-5.3-Flash-Uncensored-RCO-GSQ-GGUF GGUFGSQRCOFlashUncensored | GCSA-AiLab | ⬇ 41,852 | ♥ 11 |
| 13 | Huihui-GLM-5.3-Flash-abliterated-GGUF AbliteratedGGUFFlash | huihui-ai | ⬇ 41,766 | ♥ 405 |
| 14 | GLM-5.3-BF16 BF16 | zai-org | ⬇ 40,249 | ♥ 64 |
| 15 | LFM2.5-2.6B | LiquidAI | ⬇ 39,853 | ♥ 861 |
| 16 | GLM-5.3-Flash-BF16 BF16Flash | zai-org | ⬇ 39,617 | ♥ 85 |
| 17 | GLM-5.3-Flash-GSQ-RCO-GGUF GGUFGSQGSQ-RCORCOFlash | pfeifferj | ⬇ 37,817 | ♥ 36 |
| 18 | GLM-5.3-Flash-Maya-M-Derisked-IQ2_S-GGUF GGUFIQ2_SFlash | peasantsmith | ⬇ 37,336 | ♥ 13 |
| 19 | GLM-5.3-Flash-GGUF GGUFFlashllama.cpp | vcruz305 | ⬇ 33,158 | ♥ 4 |
| 20 | GLM-5.3-Flash-Strata-Q2Q3-Experts FlashStrata | lte-ai | ⬇ 28,871 | ♥ 5 |
| 21 | GLM-5.3-Flash-oQ4e-mtp MTPoQ4eFlash | Jundot | ⬇ 27,858 | ♥ 7 |
| 22 | GLM-5.3-Flash-Coder-RCO-152E-GGUF CoderGGUFRCOFlashllama.cpp | lapadatbogdan | ⬇ 24,868 | ♥ 37 |
| 23 | GLM5.3-Flash-E192-DGX-Spark FlashvLLM | autotrust | ⬇ 24,360 | ♥ 27 |
| 24 | GLM-5.3-Flash-abliterated-Maya-M-GGUF AbliteratedGGUFFlash | alesha-pro | ⬇ 21,109 | ♥ 11 |
| 25 | GLM-5.3-Flash-Uncensored-Q2-ds4 Q2FlashUncensored | DogContext | ⬇ 20,497 | ♥ 23 |
| 26 | GLM-5.3-Flash-Uncensored-GGUF GGUFFlashllama.cppUncensored | orcarouter | ⬇ 19,828 | ♥ 177 |
| 27 | GLM-5.3-Flash-UNCENSORED-GGUF GGUFFlashUncensored | AliceThirty | ⬇ 19,760 | ♥ 23 |
| 28 | GLM-5.3-Flash-NVFP4 NVFP4FlashvLLM | RedHatAI | ⬇ 19,102 | ♥ 51 |
| 29 | GLM-5.3-Flash-Quark-MXFP4 MXFP4FlashQuark | amd | ⬇ 16,979 | ♥ 2 |
| 30 | GLM-5.3-Flash-FP4-Local FP4Flash | nvidia | ⬇ 16,592 | ♥ 157 |
| 31 | GLM-5.3-Flash-Uncensored-FP8 FP8FlashUncensored | orcarouter | ⬇ 16,536 | ♥ 330 |
| 32 | GLM-5.3-Flash-GSQ-RCO-3.0bit-Q4Kattn-GGUF GGUFGSQGSQ-RCORCOFlash | neuralll | ⬇ 16,217 | ♥ 9 |
| 33 | GLM-5.3-Flash-UNCENSORED-FP8 FP8FlashUncensored | dealignai | ⬇ 14,104 | ♥ 186 |
| 34 | GLM-5.3-Flash-UNCENSORED-mlx-oQ4e-DFlash2 DFlashMLXoQ4eFlashUncensored | Solstice-AI | ⬇ 13,687 | ♥ 8 |
| 35 | GLM5.3-Flash-E224-DGX-Spark FlashvLLM | autotrust | ⬇ 12,136 | ♥ 74 |
| 36 | GLM-5.3-SuperExpert-v2-9.2GB llama.cppOllama | shashanth-27xA9 | ⬇ 12,081 | ♥ 10 |
| 37 | GLM-5.3-Flash-DFlash2 DFlashFlashSGLang | incoai | ⬇ 11,817 | ♥ 131 |
| 38 | GLM-5.3-Flash-GGUF-DGX-Spark GGUFFlashllama.cpp | autotrust | ⬇ 9,960 | ♥ 30 |
| 39 | GLM-5.3-Flash-UNCENSORED-mlx-oQ8e-DFlash2 DFlashMLXFlashoQ8eUncensored | Solstice-AI | ⬇ 9,897 | ♥ 11 |
| 40 | GLM-5.3-Flash-BF16-GGUF BF16GGUFFlash | bartowski | ⬇ 9,026 | ♥ 9 |
Techniques in this family
GGUFUncensoredllama.cppAbliteratedNVFP4vLLMMLXMTPSGLangFP8DFlashW4A16RCOGSQ4-bitBF16
Other model families
Qwen3.8-27BQwen · 1,128 models
ERNIE-5.5-Flash-Basebaidu · 5 models
DeepSeek-V4-Prodeepseek-ai · 460 models
DeepSeek-V4.1-Flash-1017deepseek-ai · 529 models
gemma-4-12Bgoogle · 1,135 models
gemma-4-26B-A4Bgoogle · 1,131 models
gemma-4-31Bgoogle · 1,215 models
gemma-4-E2Bgoogle · 1,229 models
gemma-4-E4Bgoogle · 1,189 models
LFM3-1.7BLiquidAI · 364 models
MiniMax-M2.5MiniMaxAI · 170 models
Kimi-K3moonshotai · 504 models
MiniCPM5-2Bopenbmb · 440 models
Qwen3.5-4B-BaseQwen · 555 models
Qwen3.5-9B-BaseQwen · 960 models
Qwen3.8-Flash-NextQwen · 1,230 models
Hy3tencent · 165 models
Inkling-2-Smallthinkingmachines · 35 models
Inkling-Smallthinkingmachines · 183 models
Inklingthinkingmachines · 341 models
GLM-5.3zai-org · 1,008 models