GGUF models by PJRM

60 GGUF models quantized by PJRM on Hugging Face. Sizes run from 1.54B to 4.51B parameters. The longest trained context is 256K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
Qwen3.8 4B Distill Heretic
Qwen · PJRM
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningTool use
LL
Llama 3.2 3B Instruct
Llama · PJRM
Params3.61B
Context128K
Smallest2.1 GB
Tool use
MI
MiniMax M2.5 Tiny 24e
Minimax · PJRM
Params4.3B
Context192K
Smallest2.6 GB
GGUF
NS
NSFW flash Q4 0
Nsfw · PJRM
Params2.24B
Context4K
Smallest1.3 GB
GGUF
LL
Dark Hermes3 Llama3.2 3B abliterated Q4 0
Llama · PJRM
Params3.61B
Context128K
Smallest2.1 GB
Tool use
GE
Nidum Gemma 2B Uncensored
Gemma · PJRM
Params2.51B
Context8K
Q4_K_M1.6 GB
GGUF
QW
Qwen3 4B Claude Sonnet 4 Reasoning Distill Heretic Abliterated Heretic Abliterated
Qwen · PJRM
Params4.02B
Context40K
Smallest2.4 GB
Reasoning
ST
stablelm 2 1 6b chat imatrix
Stablelm · PJRM
Params1.64B
Context4K
Q4_K_M1.0 GB
Tool use
PH
Phi 4 Mini Instruct Abliterated
Phi · PJRM
Params3.84B
Context128K
Smallest2.3 GB
CodingTool use
QW
Qwen3 4B Instruct Uncensored
Qwen · PJRM
Params4.02B
Context256K
Smallest2.4 GB
GGUF
ST
Stablelm Zephyr 3b Heretic
Stablelm · PJRM
Params2.8B
Context4K
Smallest1.6 GB
GGUF
DA
Danube2 1.8b WizardLM Evol V2 Unfiltered
Danube · PJRM
Params1.83B
Context8K
Smallest1.1 GB
GGUF
GE
Gemmasutra Mini 2B v1
Gemma · PJRM
Params2.61B
Context8K
Smallest1.6 GB
GGUF
GE
ProtoSex RP Gemma2 2B
Gemma · PJRM
Params2.61B
Context8K
Smallest1.6 GB
Roleplay
DO
Dolphy 1.0
Dolphy · PJRM
Params4.02B
Context256K
Smallest2.4 GB
ReasoningTool use
MI
Huihui Ministral 3 3B Instruct 2512 Abliterated
Mistral · PJRM
Params3.43B
Context256K
Q4_K_M2.1 GB
GGUF
GR
Granite 3.3 2b Instruct Literary Writer v0.1
Granite · PJRM
Params2.53B
Context128K
Smallest1.5 GB
GGUF
SU
Supreme Creative 3b
Supreme · PJRM
Params3.09B
Context32K
Smallest1.8 GB
Tool use
LL
Llama 3.1 Minitron 4B Chat Q4 K M
Llama · PJRM
Params4.51B
Context128K
Q4_K_M2.8 GB
Tool use
DA
Danube2 1.8b WizardLM Evol V2 Unfiltered
Danube · PJRM
Params1.83B
Context8K
Smallest1.1 GB
GGUF
LL
Llama 3.2 3B Instruct Chatml
Llama · PJRM
Params3.21B
Context128K
Smallest1.9 GB
GGUF
DO
Dolphy 1.0
Dolphy · PJRM
Params4.02B
Context256K
Smallest2.4 GB
ReasoningTool use
LL
Llama 3.1 Nemotron Nano 4B v1.1
Llama · PJRM
Params4.51B
Context128K
Smallest2.6 GB
Tool use
ME
MegaMix 4B Q4 0
Megamix · PJRM
Params4.51B
Context128K
Smallest2.6 GB
GGUF
AU
Aura 4B
Aura · PJRM
Params4.51B
Context128K
Smallest2.7 GB
RoleplayTool use
ST
Stablelm 2 Zephyr 1_6b
Stablelm · PJRM
Params1.64B
Context4K
Smallest1.0 GB
GGUF
CH
CharGen v3 Mini
Chargen · PJRM
Params4.51B
Context128K
Smallest2.6 GB
Roleplay
LL
WizardLM llama3.2 3b IQ4 NL
Llama · PJRM
Params3.21B
Context128K
Smallest1.9 GB
Tool use
GR
Granite 3.1 3b A800M Instruct
Granite · PJRM
Params3.3B
Context128K
Smallest1.9 GB
Tool use
NO
Capybara 3B V1.9
Nous · PJRM
Params2.8B
Context4K
Smallest1.6 GB
GGUF

About PJRM on Hugging Face

PJRM has published 60 GGUF models that ggufmodels.com tracks, across families such as Llama, Qwen and Stablelm. The most downloaded are Qwen3.8 4B Distill Heretic, Llama 3.2 3B Instruct and MiniMax M2.5 Tiny 24e.

The quants PJRM publishes most often are Q4_0 (36), IQ4_NL (15), Q4_K_M (10) and Q6_K (1). Their Q4_K_M files range from 1.0 to 2.8 GB. Parameter counts run from 1.54B to 4.51B, and the longest trained context window is 256K tokens.

Frequently asked questions

What GGUF models has PJRM published?

60 models are listed here, mainly from the Llama, Qwen and Stablelm families. The most downloaded is Qwen3.8 4B Distill Heretic.

Which quants does PJRM publish?

The most common are Q4_0 (36 models), IQ4_NL (15 models), Q4_K_M (10 models) and Q6_K (1 models).

Keep browsing