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 3.1 SuperNova Lite Lorabilterated 8B
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
LL
Awanllm-Llama-3-8B-Instruct-DPO-v0.1
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Natsumura Storytelling Rp 1.0 Llama 3.1 8b
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
Roleplay
LL
Dracarys Llama 3.1 70B Instruct
Llama · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
LL
Aion RP Llama 3.1 8B
Llama · aion-labs
Params8.03B
Context128K
Smallest3.2 GB
Roleplay
LL
Llama 3 Smaug 8B
Llama · MaziyarPanahi
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama-medx_v3.1
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama 3 8B Ultra Instruct
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama 3 Swallow 8B Instruct v0.1 kokoroe i1
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama 3 Experiment v1 9B
Llama · mradermacher
Params8.9B
Context8K
Q4_K_M5.4 GB
GGUF
LL
ProjectHuman Llama3.2 1B
Llama · mradermacher
Params1.24B
Context128K
Q4_K_M0.8 GB
Tool use
LL
Llama3Ternary_10b
Llama · mradermacher
Params9.64B
Context8K
Smallest2.5 GB
GGUF
LL
BRAG Llama 3.1 8b v0.1
Llama · QuantFactory
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
LL
DataPilot Llama3.1 ArrowSE v0.4
Llama · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
LL
Blackjack-Llama3-21B
Llama · mradermacher
Params21.3B
Context8K
Q4_K_M12.9 GB
GGUF
LL
Fireball Alpaca Llama3.1.08 8B Philos C R2
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
LL
Llama3 8B Aifeifei 1.0
Llama · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
OpenMath-CodeLlama-13b-Python-hf
Llama · Mungert
Params13B
Context16K
Q4_K_M7.8 GB
Coding
LL
R1 1776 Distill Llama 70b
Llama · unsloth
Params70.6B
Context128K
Q4_K_M42.5 GB
ReasoningTool use
LL
EndConvo health 1b GGUF v1
Llama · ProdocAI
Params1.5B
Context128K
Smallest1.0 GB
Tool use
LL
Llama4Some-SOVL-4x8B-L3-V1
Llama · mradermacher
Params24.9B
Context8K
Q4_K_M15.2 GB
GGUF
LL
Llama 3 Taiwan 8B Instruct DPO
Llama · chienweichang
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama 3.2 1B Instruct
Llama · SanctumAI
Params1.24B
Context128K
Q4_K_M0.8 GB
Tool use
LL
Llama 3.2 1b English Persian Translator
Llama · Sheikhaei
Params1.24B
Context128K
Smallest1.3 GB
GGUF
LL
Alpaca Llama3.1 8B
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
LL
Llama-3-Umbral-Mind-Replete-8B
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama3.2 3b cybersecurity abliterated
Llama · DexopT
Params3.21B
Context128K
Q4_K_M2.0 GB
Tool use
LL
Llama 3 7b uncensor sanitized alpha02 gen10000 i1
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama-3-70B-Instruct-norefusal
Llama · mradermacher
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
LL
Llama eus 8B
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF

Keep browsing