Model Follower.

Up to date

Rebuilt
2026-10-25 06:54 UTC
Release radar
117 on watch
Hub snapshot
2026-10-25
Re-checked
daily · every number sourced and dated

Home › Families › meta-llama

Llama meta-llama

LLMs 4 members 87 derivatives on the Hub Last verified 2026-10-25 RSS

quantized: 62finetune: 17adapter: 8

Which ones matter

Picks are rule-based from observed data (score, downloads, size, hosting); they are not quality verdicts.

Members 4

Size
4 rows
# Model Org Role Params Band MoE License ContextProviders Price from Likes Likes 7d Downloads 30d Modified
213 Llama-Guard-3-8B meta-llama Fine-tuned from meta-llama/Llama-3.… 8.03B M dense Llama 3.1 Community License —2 — 343 +4 27.8k 2024-10-11
337 Llama-Guard-4-12B meta-llama Original model 12.0B L dense Llama Community License (ll… 160K2 $0.14 133 +1 43.3k 2025-04-29
668 Llama-Guard-3-1B meta-llama Original model 1.50B S dense Llama 3.2 Community License —0 — 133 +3 27.6k 2024-09-26
680 Meta-Llama-Guard-2-8B meta-llama Original model 8.03B M dense Llama 3 Community License —1 — 316 0 1.9k 2024-05-13

Variants 87 shown of 87

Quantizations, fine-tunes, merges, and adapters of any member, ranked by downloads + likes. Filter by relation, quant family, or size band.

Relation
Quant
Size
87 rows
Variant Of Relation Quant Params Band License Author Likes Downloads
AcuteShrewdSecurity/Llama-Phishsense-1B meta-llama/Llama-Guard-3-1B finetune — 1.24B S llama3.2 AcuteShrewdSecurity 10 54k
legraphista/Llama-Guard-3-8B-IMat-GGUF meta-llama/Llama-Guard-3-8B quantized GGUF — — llama3.1 legraphista 5 40.8k
eaddario/Llama-Guard-3-8B-GGUF meta-llama/Llama-Guard-3-8B quantized GGUF — — llama3.1 eaddario 0 20.4k
mradermacher/Llama-Guard-3-8B-i1-GGUF meta-llama/Llama-Guard-3-8B quantized GGUF — — llama3.1 mradermacher 5 18.2k
QuantFactory/Meta-Llama-Guard-2-8B-GGUF meta-llama/Meta-Llama-Guard-2-8B quantized GGUF — — other QuantFactory 12 16.7k
mradermacher/Llama-Guard-3-8B-GGUF meta-llama/Llama-Guard-3-8B quantized GGUF — — llama3.1 mradermacher 1 15k
tybrs/llama-guard-quant meta-llama/Meta-Llama-Guard-2-8B quantized -quant — — other tybrs 0 12.3k
jpodivin/Meta-Llama-Guard-2-8B-GGUF meta-llama/Meta-Llama-Guard-2-8B quantized GGUF — — other jpodivin 0 5.7k
VincentGOURBIN/Llama-Guard-3-8B meta-llama/Llama-Guard-3-8B finetune — 8.03B M llama3.1 VincentGOURBIN 0 5.1k
Rakancorle1/ThinkGuard meta-llama/Llama-Guard-3-8B finetune — 8.03B M llama3.1 Rakancorle1 4 3.7k
featherless-ai-quants/meta-llama-Llama-Guard-3-8B-GGUF meta-llama/Llama-Guard-3-8B quantized GGUF — — — featherless-ai-quants 0 2.6k
tensorblock/Llama-Guard-3-1B-GGUF meta-llama/Llama-Guard-3-1B quantized GGUF — — llama3.2 tensorblock 1 2.5k
solidrust/Meta-Llama-Guard-2-8B-AWQ meta-llama/Meta-Llama-Guard-2-8B quantized AWQ 8.03B M other solidrust 0 2.6k
tensorblock/Llama-Guard-3-8B-GGUF meta-llama/Llama-Guard-3-8B quantized GGUF — — llama3.1 tensorblock 0 2.5k
DevQuasar-8/meta-llama.Llama-Guard-3-8B-GGUF meta-llama/Llama-Guard-3-8B quantized GGUF — — — DevQuasar-8 1 2.3k
tensorblock/Meta-Llama-Guard-2-8B-GGUF meta-llama/Meta-Llama-Guard-2-8B quantized GGUF — — llama3 tensorblock 0 2.2k
MaziyarPanahi/Llama-Guard-3-8B-GGUF meta-llama/Llama-Guard-3-8B quantized GGUF — — — MaziyarPanahi 0 2.1k
MaziyarPanahi/Llama-Guard-3-1B-GGUF meta-llama/Llama-Guard-3-1B quantized GGUF — — — MaziyarPanahi 0 1.9k
DevQuasar-8/meta-llama.Meta-Llama-Guard-2-8B-GGUF meta-llama/Meta-Llama-Guard-2-8B quantized GGUF — — — DevQuasar-8 0 1.8k
DevQuasar/meta-llama.Llama-Guard-4-12B-GGUF meta-llama/Llama-Guard-4-12B quantized GGUF — — — DevQuasar 0 1.5k
DevQuasar-2/Llama-Guard-3-1B-GGUF meta-llama/Llama-Guard-3-1B quantized GGUF — — — DevQuasar-2 0 1.1k
leliuga/Meta-Llama-Guard-2-8B-bnb-4bit meta-llama/Meta-Llama-Guard-2-8B quantized -bnb 8.25B M other leliuga 1 878
itlwas/Llama-Guard-3-1B-Q4_K_M-GGUF meta-llama/Llama-Guard-3-1B quantized GGUF — — llama3.2 itlwas 0 774
onnx-community/Llama-Guard-3-1B meta-llama/Llama-Guard-3-1B quantized — — — llama3.2 onnx-community 2 657
DevQuasar/meta-llama.Llama-Guard-3-1B-GGUF meta-llama/Llama-Guard-3-1B quantized GGUF — — — DevQuasar 0 695
SirSahOl/Llama-Guard-3-1B-chat-mlx-16bit meta-llama/Llama-Guard-3-1B finetune mlx 1.50B S llama3.2 SirSahOl 0 633
smdesai/llama-guard-3-1b meta-llama/Llama-Guard-3-1B quantized — 1.50B S llama3.2 smdesai 0 508
Fabio2000/Llama-Guard-3-8B-Q4_K_M-GGUF meta-llama/Llama-Guard-3-8B quantized GGUF — — llama3.1 Fabio2000 0 384
itlwas/Meta-Llama-Guard-2-8B-Q4_K_M-GGUF meta-llama/Meta-Llama-Guard-2-8B quantized GGUF — — llama3 itlwas 1 326
itlwas/Llama-Guard-3-8B-Q4_K_M-GGUF meta-llama/Llama-Guard-3-8B quantized GGUF — — llama3.1 itlwas 0 364
tengsnake/Llama-Guard-4-12B-NVFP4 meta-llama/Llama-Guard-4-12B quantized NVFP4 12.0B L llama4 tengsnake 3 201
ktoprakucar/Llama-Guard-3-8B-Q8-GPTQ meta-llama/Llama-Guard-3-8B quantized GPTQ — — llama3.1 ktoprakucar 1 283
lauraharyo/Llama-Guard-3-8B-Q4_K_M-GGUF meta-llama/Llama-Guard-3-8B quantized GGUF — — llama3.1 lauraharyo 0 332
venkatsriram/Llama-Guard-3-8B-Q4_K_M-GGUF meta-llama/Llama-Guard-3-8B quantized GGUF — — llama3.1 venkatsriram 1 272
Fabio2000/Llama-Guard-3-1B-Q4_K_M-GGUF meta-llama/Llama-Guard-3-1B quantized GGUF — — llama3.2 Fabio2000 0 269
thegenerativegeneration/Llama-Guard-3-8B-Q2_K-GGUF meta-llama/Llama-Guard-3-8B quantized Q2_K — — llama3.1 thegenerativegeneration 0 257
AIFunOver/Llama-Guard-3-1B-openvino-8bit meta-llama/Llama-Guard-3-1B quantized -8bit — — llama3.2 AIFunOver 0 242
GuardwallAI/Llama-Guard-3-8B-Q4_K_M-GGUF meta-llama/Llama-Guard-3-8B quantized GGUF — — llama3.1 GuardwallAI 0 239
samuellimabraz/Llama-Guard-3-1B-Q4_K_M-GGUF meta-llama/Llama-Guard-3-1B quantized GGUF — — llama3.2 samuellimabraz 0 234
Thorge-AI/llama-guard-3-1b-q8_0.gguf meta-llama/Llama-Guard-3-1B quantized q8_0 — — llama3.2 Thorge-AI 1 183
mlx-community/Llama-Guard-3-1B-chat-mlx-16bit meta-llama/Llama-Guard-3-1B finetune mlx 1.50B S llama3.2 mlx-community 0 216
jquirion/Llama-Guard-3-1B-Q4_K_M meta-llama/Llama-Guard-3-1B quantized GGUF — — llama3.2 jquirion 0 211
sheldonrobinson/Llama-Guard-3-1B-Q8_0-GGUF meta-llama/Llama-Guard-3-1B quantized Q8_0 — — llama3.2 sheldonrobinson 0 155
GuardwallAI/Llama-Guard-3-8B-Q8_0-GGUF meta-llama/Llama-Guard-3-8B quantized Q8_0 — — llama3.1 GuardwallAI 0 153
wolfCuanhamaRWS/GuardReasoner-1B_q5_k_m_gguf meta-llama/Llama-Guard-3-1B quantized gguf — — llama3.2 wolfCuanhamaRWS 0 150
GuardwallAI/Llama-Guard-3-1B-Q8_0-GGUF meta-llama/Llama-Guard-3-1B quantized Q8_0 — — llama3.2 GuardwallAI 0 149
mlx-community/Llama-Guard-3-1B-chat-mlx-8bit meta-llama/Llama-Guard-3-1B quantized mlx 1.50B S llama3.2 mlx-community 0 148
marcusnogueira/llama-guard-3-8b-awq-4bit meta-llama/Llama-Guard-3-8B quantized awq 8.03B M — marcusnogueira 0 141
tomalamb/Llama-Guard-3-1B-lora-r1-beavertails meta-llama/Llama-Guard-3-1B adapter — — — — tomalamb 0 141
marcusnogueira/llama-guard-3-1b-awq-4bit meta-llama/Llama-Guard-3-1B quantized awq 1.50B S — marcusnogueira 0 139
mlx-community/Llama-Guard-3-1B-chat-mlx-4bit meta-llama/Llama-Guard-3-1B quantized mlx 1.50B S llama3.2 mlx-community 0 137
marcusnogueira/llama-guard-3-8b-gptq-4bit meta-llama/Llama-Guard-3-8B quantized gptq 8.03B M — marcusnogueira 0 136
liao1111/CompanionGuard meta-llama/Llama-Guard-3-8B adapter — — — other liao1111 2 35
marcusnogueira/llama-guard-3-8b-gptq-8bit meta-llama/Llama-Guard-3-8B quantized gptq 8.03B M — marcusnogueira 0 134
Tibi29/Llama-Guard-3-1B-Phishing-Fine-Tune meta-llama/Llama-Guard-3-1B finetune — 1.24B S llama3.2 Tibi29 0 132
Anthonyg5005/Llama-Guard-3-1B-exl2 meta-llama/Llama-Guard-3-1B quantized exl2 — — llama3.2 Anthonyg5005 0 125
sheldonrobinson/Llama-Guard-3-1B-Q4_0-GGUF meta-llama/Llama-Guard-3-1B quantized Q4_0 — — llama3.2 sheldonrobinson 0 111
bricknerdev/Llama-Guard-3-1B-Q8_0-GGUF meta-llama/Llama-Guard-3-1B quantized Q8_0 — — llama3.2 bricknerdev 0 103
martintomov/Meta-Llama-Guard-2-8B-Q8_0-GGUF meta-llama/Meta-Llama-Guard-2-8B quantized Q8_0 — — llama3 martintomov 0 103
AIFunOver/Llama-Guard-3-1B-openvino-4bit meta-llama/Llama-Guard-3-1B quantized -4bit — — llama3.2 AIFunOver 0 78
marcusnogueira/llama-guard-3-1b-gptq-4bit meta-llama/Llama-Guard-3-1B quantized gptq 1.50B S — marcusnogueira 0 77
marcusnogueira/llama-guard-3-1b-gptq-8bit meta-llama/Llama-Guard-3-1B quantized gptq 1.50B S — marcusnogueira 0 70
Anthonyg5005/Meta-Llama-Guard-2-8B-exl2 meta-llama/Meta-Llama-Guard-2-8B quantized exl2 — — other Anthonyg5005 0 70
SirSahOl/Llama-Guard-3-1B-chat-mlx-4bit meta-llama/Llama-Guard-3-1B quantized mlx 1.50B S llama3.2 SirSahOl 0 67
AIFunOver/Llama-Guard-3-1B-openvino-fp16 meta-llama/Llama-Guard-3-1B finetune -fp16 — — llama3.2 AIFunOver 0 64
wolfCuanhamaRWS/Llama-Phishsense-1B_q4_k_m_gguf meta-llama/Llama-Guard-3-1B quantized gguf — — llama3.2 wolfCuanhamaRWS 0 63
SirSahOl/Llama-Guard-3-1B-chat-mlx-8bit meta-llama/Llama-Guard-3-1B quantized mlx 1.50B S llama3.2 SirSahOl 0 61
jainsatyam26/nemotron-llamaguard-final meta-llama/Llama-Guard-3-1B adapter — — — — jainsatyam26 0 54
tomalamb/Llama-Guard-3-8B-lora-r1-beavertails meta-llama/Llama-Guard-3-8B adapter — — — — tomalamb 0 49
2084Collective/sft_output meta-llama/Llama-Guard-3-1B finetune — 1.50B S — 2084Collective 0 49
Timios74/aegisguard-llama-guard meta-llama/Llama-Guard-3-1B finetune — 1.24B S mit Timios74 0 40
aascott/Llama-Guard-3-1B-Confusable-Guard-LoRA meta-llama/Llama-Guard-3-1B adapter — — — llama3.2 aascott 0 29
IronMan70ny/llama-guard-custom meta-llama/Meta-Llama-Guard-2-8B adapter — — — llama3 IronMan70ny 0 26
mitulr/outputs meta-llama/Llama-Guard-3-1B adapter — — — llama3.2 mitulr 0 25
Rakancorle1/laaj_15k_label_only meta-llama/Llama-Guard-3-8B adapter — — — llama3.1 Rakancorle1 0 22
jackysnake/sft_gr-llama_guard_3_8b meta-llama/Llama-Guard-3-8B finetune — 8.03B M other jackysnake 0 20
marcusnogueira/llama-guard-3-8b-llm-int8 meta-llama/Llama-Guard-3-8B quantized int8 8.03B M — marcusnogueira 0 18
marcusnogueira/llama-guard-3-1b-smoothquant-w8a8 meta-llama/Llama-Guard-3-1B quantized -w8a8 1.50B S — marcusnogueira 0 16
marcusnogueira/llama-guard-3-8b-smoothquant-w8a8 meta-llama/Llama-Guard-3-8B quantized -w8a8 8.03B M — marcusnogueira 0 15
marcusnogueira/llama-guard-3-1b-llm-int8 meta-llama/Llama-Guard-3-1B quantized int8 1.50B S — marcusnogueira 0 15
jackysnake/sft_gr-meta_llama_guard_2_8b meta-llama/Meta-Llama-Guard-2-8B finetune — 8.03B M other jackysnake 0 8
jodel/finetune-guard-3 meta-llama/Llama-Guard-3-8B finetune — — — other jodel 0 0
44m0n/llama-guard-3-sensitive-data-0-1 meta-llama/Llama-Guard-3-8B finetune — — — other 44m0n 0 0
saiteki-kai/QA-Llama-Guard-3-8B meta-llama/Llama-Guard-3-8B finetune — — — — saiteki-kai 0 0
wolfCuanhamaRWS/Llama-Phishsense-1B-GGUF meta-llama/Llama-Guard-3-1B finetune GGUF — — llama3.2 wolfCuanhamaRWS 0 0
Arittroskr3232/llama-guard-3-1b-secure-rag meta-llama/Llama-Guard-3-1B finetune — — — llama3.1 Arittroskr3232 0 0
JosineyJr/generate-conventional-commit-messages meta-llama/Meta-Llama-Guard-2-8B finetune — — — apache-2.0 JosineyJr 0 0

Get alerts on the Llama family

Watch this family

Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.