Hugging Face model family · Qwen
Qwen3.8-27B model family
Trace Qwen3.8-27B and its 1,127 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 Qwen3.8-27B.
Open interactive lineage graph → Browse all families
1,128 models in family
384 GGUF variants
7,094,218 base downloads
2026-08-05 base released
Popular Qwen3.8-27B derivatives
| # | Model | Author | Downloads | Likes |
|---|---|---|---|---|
| 1 | Qwen3.8-27B-GGUF GGUF | unsloth | ⬇ 6,097,719 | ♥ 5,795 |
| 2 | Qwen3.8-27B-FP8 FP8 | Qwen | ⬇ 5,442,810 | ♥ 984 |
| 3 | Huihui-Qwen3.8-27B-abliterated-GGUF AbliteratedGGUF | huihui-ai | ⬇ 4,011,565 | ♥ 2,032 |
| 4 | Qwen3.8-27B-iMatrix-NVFP4-MTP-GGUF GGUFiMatrixMTPNVFP4llama.cpp | cdiamond | ⬇ 3,271,044 | ♥ 50 |
| 5 | Qwen3.8-27B-MLX-4bit 4-bitMLX | lmstudio-community | ⬇ 2,893,081 | ♥ 124 |
| 6 | Qwen3.8-27B-MLX-8bit 8-bitMLX | lmstudio-community | ⬇ 2,737,587 | ♥ 56 |
| 7 | Qwen3.8-27B-MLX-6bit 6-bitMLX | lmstudio-community | ⬇ 2,715,043 | ♥ 44 |
| 8 | Qwen3.8-27B-MLX-5bit 5-bitMLX | lmstudio-community | ⬇ 2,712,201 | ♥ 19 |
| 9 | Qwen3.8-27B-Uncensored-GGUF GGUFllama.cppUncensored | JonathanColetti | ⬇ 2,346,519 | ♥ 1,977 |
| 10 | Qwen3.8-27B-GGUF GGUF | byteshape | ⬇ 2,083,628 | ♥ 215 |
| 11 | Qwen3.8-27B-NVFP4 NVFP4 | unsloth | ⬇ 1,939,275 | ♥ 540 |
| 12 | Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF GGUFMTPAggressiveUncensored | HauhauCS | ⬇ 1,831,413 | ♥ 2,486 |
| 13 | Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF GGUFGSQGSQ-RCORCOllama.cpp | ukisai | ⬇ 1,605,909 | ♥ 512 |
| 14 | Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF CoderGGUFHereticMTPCold-Fusion | DavidAU | ⬇ 1,599,836 | ♥ 2,968 |
| 15 | Ternary-Bonsai-2-27B-gguf GGUFTernaryllama.cpp | prism-ml | ⬇ 1,541,289 | ♥ 2,998 |
| 16 | AutoTrust-Decider-Pro-Vision-27B deciderVisionvLLM | autotrust | ⬇ 1,537,390 | ♥ 4,522 |
| 17 | Dirk-Qwen3.8-27B-GGUF GGUFllama.cpp | peculiar-ragdoll | ⬇ 1,395,782 | ♥ 271 |
| 18 | Qwen3.8-27B-GSQ-RCO-GGUF GGUFGSQGSQ-RCORCO | ISTA-DASLab | ⬇ 1,358,588 | ♥ 2,739 |
| 19 | Swift-1.5-Qwen3.8-27B-heretic-GSQ-RCO-GGUF GGUFGSQGSQ-RCOHereticRCO | jegreene | ⬇ 1,185,252 | ♥ 34 |
| 20 | Qwen3.8-27B-Heretic-Abliterated-Uncensored-GGUF AbliteratedGGUFHereticUncensored | 0bserverx | ⬇ 1,131,796 | ♥ 874 |
| 21 | Qwen3.8-27B-GGUF GGUF | lmstudio-community | ⬇ 1,081,301 | ♥ 102 |
| 22 | Qwen3.8-27B-AWQ-INT4 AWQINT4 | cyankiwi | ⬇ 1,056,172 | ♥ 135 |
| 23 | Qwen3.8-27B-Turbo-Brilliance-50X-Reasoning-Instruct-NEO-MAX-MTP-GGUF GGUFInstructMTPReasoningBrilliance | DavidAU | ⬇ 1,053,462 | ♥ 303 |
| 24 | Qwen3.8-27B-GGUF GGUF | ggml-org | ⬇ 1,000,687 | ♥ 157 |
| 25 | Qwen3.8-27B-NVFP4 NVFP4 | RadixArk | ⬇ 986,112 | ♥ 126 |
| 26 | Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-MTP-DFlash2 DFlashMTPCoder390EfficientThinkvLLM | nerkyor | ⬇ 925,624 | ♥ 557 |
| 27 | Qwen3.8-27B-AP-GGUF GGUF | agentionai | ⬇ 921,817 | ♥ 103 |
| 28 | ThinkingCap-Qwen3.8-27B-GGUF GGUFllama.cppThinkingCap | bottlecapai | ⬇ 900,355 | ♥ 97 |
| 29 | Qwen3.8-27B-Fable-5-Coding-Distilled-GGUF CoderGGUFDistilled | mradermacher | ⬇ 898,645 | ♥ 34 |
| 30 | Qwen3.8-27B-Defiance-Uncensored-MTP-GGUF GGUFMTPllama.cppUncensored | ttindall | ⬇ 671,223 | ♥ 215 |
| 31 | Qwen3.8-27B-Uncensored-Cyber-GGUF GGUFCyberllama.cppUncensored | philbert440 | ⬇ 558,073 | ♥ 79 |
| 32 | Qwen3.8-27B-OBLITERATED OBLITERATED | OBLITERATUS | ⬇ 542,388 | ♥ 1,666 |
| 33 | Qwen3.8-27B-DFlash2-GGUF DFlashGGUFllama.cpp | z-lab | ⬇ 500,507 | ♥ 160 |
| 34 | Qwen3.8-27B-Jumbo-Fusion-IQ-747-900-Turbo-Brilliance-50X-Reasoning-Instruct-NEO-MAX-MTP-GGUF GGUFInstructMTPReasoningBrilliance | DavidAU | ⬇ 477,227 | ♥ 57 |
| 35 | Swift-Qwen3.8-27B-GGUF GGUFllama.cppSwift | ukisai | ⬇ 458,387 | ♥ 477 |
| 36 | AutoTrust-Decider-Pro-27B decidervLLM | autotrust | ⬇ 449,525 | ♥ 487 |
| 37 | Qwen3.8-27B-DFlash2 DFlashvLLMSGLang | incoai | ⬇ 429,580 | ♥ 301 |
| 38 | Qwen3.8-27B-Cold-Fusion-GAIN-V1.1-NM-DAU-NEO-MAX-MTP-GGUF GGUFMTPCold-FusionGAINMAX | DavidAU | ⬇ 372,115 | ♥ 342 |
| 39 | Qwen3.8-27B-Uncensored-Cyber-agentic-imatrix-GGUF AgenticGGUFiMatrixCyberllama.cpp | cyjin-yl | ⬇ 315,587 | ♥ 260 |
| 40 | Qwen3.8-27B-MTP-NVFP4 MTPNVFP4vLLM | sakamakismile | ⬇ 312,862 | ♥ 46 |
Techniques in this family
GGUFllama.cppUncensoredvLLMMTPNVFP4AbliteratedHereticGSQGSQ-RCORCOSwiftNInferNEOTurboAWQ
Other model families
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-5.3-Flashzai-org · 645 models
GLM-5.3zai-org · 1,008 models