Llama GGUF models

30050 GGUF models in the Llama family, quantized by 7365 uploaders. Sizes run from 1M to 1020B parameters. The longest trained context is 102400K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
LL
Llama 3.3 8B Abliterated
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
LiquidAI LFM2.5 350M b2b llamacpp
Llama · damienlusson
Params354M
Context125K
Q4_K_M0.2 GB
ReasoningTool use
LL
chinese llama 2 1.3b
Llama · hfl
Params1.26B
Context4K
Smallest0.6 GB
GGUF
LL
Pair Preference Model LLaMA3 8B
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Yi 6B 200K Llama
Llama · mradermacher
Params6.06B
Context195K
Q4_K_M3.7 GB
GGUF
LL
Llama_3.x_70b_L3.3 Dolphin Eva_fusion_v2
Llama · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
LL
Llama SEA LION v3 8B IT
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
LL
Llama 3 8B OpenHermes 2.5 1M
Llama · QuantFactory
Params8.03B
Context8K
Q4_K_M4.9 GB
Tool use
LL
Dolphin 3.0 Llama 3.2 1b
Llama · itlwas
Params1.24B
Context128K
Q4_K_M0.8 GB
CodingTool use
LL
Llama 3.3 70b DarkHorse i1
Llama · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
Tool use
LL
Trendyol LLM 8b Chat v2.0
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama 3.1 8B ArliAI Formax v1.0
Llama · Lewdiculous
Params8.03B
Context128K
Q4_K_M4.9 GB
Roleplay
LL
Llama3.2 24B A3B II Dark Champion INSTRUCT Heretic Abliterated Uncensored
Llama · Hwk123456
Params18B
Context128K
Q4_K_M11.1 GB
RoleplayTool use
LL
deepfake research llama3.2 3b
Llama · SaliElloh
Params3.21B
Context128K
Q4_K_M2.0 GB
Tool use
LL
Progenitor V2.3 LLaMa 70B
Llama · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
Tool use
LL
Llama3 OrpoSmaug Slerp 8B
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama_3.x_70b_Hexagon_Purple_V3
Llama · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
Tool use
LL
ArliAI-Llama-3-8B-Instruct-Dolfin-v0.1
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama3 8b It Translation General En Ko 1sent
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama 3.1 8B Instruct Abliterated_Via_Adapter
Llama · grimjim
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
LL
dolphin-2.9-llama3-8b-1m
Llama · bartowski
Params8.03B
Context1024K
Q4_K_M4.9 GB
CodingTool use
LL
Heretic Dirty Alice RP NSFW Llama 3.2 1B
Llama · mradermacher
Params1.24B
Context128K
Q4_K_M0.8 GB
Roleplay
LL
Meta-Llama-3-70B-Instruct
Llama · lmstudio-community
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
LL
Dolphin 3.0 Llama 3.1 8B
Llama · QuantFactory
Params8.03B
Context128K
Q4_K_M4.9 GB
CodingTool use
LL
Llama 3.3 8B Instruct 128K
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
LL
Yin Base LLaMa 70B i1
Llama · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
Tool use
LL
Llama3 8B Chinese Chat
Llama · pravdin
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama 3 SynE
Llama · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Cakrawala Llama 3.1 70B i1
Llama · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
LL
Deep Reasoning Llama 3.2 JametMini 3B MK.III i1
Llama · mradermacher
Params3.21B
Context128K
Q4_K_M2.0 GB
ReasoningTool use

Keep browsing