GGUF models by MaziyarPanahi

1376 GGUF models quantized by MaziyarPanahi on Hugging Face. Sizes run from 10M to 671B parameters. The longest trained context is 1024K tokens.

Most downloadedNewestLargestLongest contextSmallest
FA
Models Tiiuae Falcon3 1B Instruct
Falcon · MaziyarPanahi
Params1.67B
Context8K
Smallest1.2 GB
GGUF
MI
speechless code mistral orca 7b v1.0 Mistral 7B Instruct v0.1
Mistral · MaziyarPanahi
Params7.24B
Context32K
Q4_K_M4.4 GB
Coding
LL
Llama 3.2 3b Kermes v2
Llama · MaziyarPanahi
Params3.21B
Context128K
Smallest2.3 GB
GGUF
MI
mistral sk 7b
Mistral · MaziyarPanahi
Params7.24B
Context32K
Smallest5.0 GB
GGUF
MI
SauerkrautLM 7b HerO Mistral 7B Instruct v0.1
Mistral · MaziyarPanahi
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
MI
Mini synatra 7b 02 Mistral 7B Instruct v0.2 slerp
Mistral · MaziyarPanahi
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
KU
Kunoichi 7B
Kunoichi · MaziyarPanahi
Params7.24B
Context8K
Q4_K_M4.4 GB
GGUF
QW
Models Benchang1110 Qwen2.5 Taiwan 3B Reason SFT
Qwen · MaziyarPanahi
Params3.4B
Context32K
Smallest2.4 GB
ReasoningTool use
YU
Yuna Ai V4
Yuna · MaziyarPanahi
Params8.03B
Context128K
Smallest5.6 GB
GGUF
UN
UnslopNemo v4.1 Magnum v4 12B
Unslopnemo · MaziyarPanahi
Params12.2B
Context1000K
Smallest8.5 GB
GGUF
MI
Mistral Nemo Prism 12B v2
Mistral · MaziyarPanahi
Params12.2B
Context1000K
Smallest8.5 GB
GGUF
QW
Rombos LLM V2.5 Qwen 7b
Qwen · MaziyarPanahi
Params7.62B
Context128K
Smallest5.3 GB
Tool use
QW
Models QuantPanda Qwen2.5.1 Coder 1.5B Instruct
Qwen · MaziyarPanahi
Params1.54B
Context32K
Smallest1.1 GB
CodingTool use
MI
bagel dpo 7b v0.1 Mistral 7B Instruct v0.1
Mistral · MaziyarPanahi
Params7.24B
Context32K
Q4_K_M4.4 GB
Coding
MI
Models Rhyang2021 Uncertain_Mistral_7B
Mistral · MaziyarPanahi
Params7.24B
Context32K
Smallest5.0 GB
GGUF
QW
Qwen2.5 14B
Qwen · MaziyarPanahi
Params14.8B
Context128K
Smallest10.3 GB
Tool use
CO
Iq Code Evmind 14b Instruct v0.2411.2
Code · MaziyarPanahi
Params14.8B
Context32K
Smallest10.3 GB
CodingTool use
MI
CollectiveCognition v1 Mistral 7B Mistral 7B Instruct v0.1
Mistral · MaziyarPanahi
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
DE
Deepthink Reasoning 7B
Deepthink · MaziyarPanahi
Params7.62B
Context32K
Smallest5.3 GB
ReasoningTool use
GR
GritLM 8x7B
Gritlm · MaziyarPanahi
Params46.7B
Context32K
Q4_K_M28.4 GB
Coding
VI
Virtuoso Small
Virtuososmall · MaziyarPanahi
Params14.8B
Context128K
Smallest10.3 GB
Tool use
RQ
RQwen v0.1
Rqwen · MaziyarPanahi
Params14.8B
Context32K
Smallest10.3 GB
Tool use
LL
models--mergekit-community--TopStarClaudioArena
Llama · MaziyarPanahi
Params7.24B
Context32K
Q4_K_M4.4 GB
Tool use
QW
calme 2.3 qwen2 7b
Qwen · MaziyarPanahi
Params7.62B
Context128K
Q4_K_M4.7 GB
GGUF
YA
models--automerger--YamYam-7B
Yam · MaziyarPanahi
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
CA
models--mergekit-community--mergekit-slerp-exkkzvd
Calme · MaziyarPanahi
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
NE
TQ2.5 14B Neon v1
Neon · MaziyarPanahi
Params14.8B
Context128K
Smallest10.3 GB
Tool use
MI
Mistral Trismegistus 7B Mistral 7B Instruct v0.2 slerp
Mistral · MaziyarPanahi
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
VI
Models prithivMLmods Viper Coder Hybrid v1.2
Viper · MaziyarPanahi
Params14.8B
Context32K
Smallest10.3 GB
CodingTool use
LL
LLaMA 3 8B GRPO Finance Math TR
Llama · MaziyarPanahi
Params8.03B
Context8K
Smallest5.6 GB
GGUF

Keep browsing