GGUF models by DevQuasar-8
86 GGUF models quantized by DevQuasar-8 on Hugging Face. Sizes run from 362M to 671B parameters. The longest trained context is 1000K tokens.
DE
AXCXEPT.phi 4 Deepseek R1K RL EZO
DeepSeek · DevQuasar-8
Params14.7B
Context16K
Q4_K_M9.1 GB
QW
Qwen.Qwen2 0.5B
Qwen · DevQuasar-8
Params494M
Context128K
Q4_K_M0.4 GB
SK
NovaSky AI.Sky T1 7B
Sky · DevQuasar-8
Params7.62B
Context4K
Q4_K_M4.7 GB
MI
teknium.Hermes Trismegistus Mistral 7B
Mistral · DevQuasar-8
Params7.24B
Context32K
Q4_K_M4.4 GB
OP
allenai.open instruct stanford alpaca 7b
Open · DevQuasar-8
Params6.74B
Context2K
Q4_K_M4.1 GB
LL
Huihui ai.Llama 3_1 Nemotron 51B Instruct Abliterated
Llama · DevQuasar-8
Params51.5B
Context128K
Q4_K_M31.0 GB
LL
Huihui ai.Tess R1 Limerick Llama 3.1 70B Abliterated
Llama · DevQuasar-8
Params70.6B
Context128K
Q4_K_M42.5 GB
PR
teknium.SD PrompTune v1
Promptune · DevQuasar-8
Params7.24B
Context32K
Q4_K_M4.4 GB
MI
teknium.Mistral Trismegistus 7B
Mistral · DevQuasar-8
Params7.24B
Context32K
Q4_K_M4.4 GB
MA
Magellanic Opus 14B Exp
Magellanic · DevQuasar-8
Params14.8B
Context128K
Q4_K_M9.0 GB
QW
Qwen.Qwen2 Math 1.5B Instruct
Qwen · DevQuasar-8
Params1.54B
Context4K
Q4_K_M1.0 GB
QW
Qwen.Qwen1.5 4B
Qwen · DevQuasar-8
Params3.95B
Context32K
Q4_K_M2.5 GB
GE
Malteos.German R1
German · DevQuasar-8
Params3.09B
Context32K
Q4_K_M1.9 GB
QW
Qwen.Qwen1.5 1.8B
Qwen · DevQuasar-8
Params1.84B
Context32K
Q4_K_M1.2 GB
LE
DeepMount00.Lexora Lite 3B
Lexora · DevQuasar-8
Params3.09B
Context32K
Q4_K_M1.9 GB
EX
LGAI EXAONE.EXAONE 3.5 2.4B Instruct
Exaone · DevQuasar-8
Params2.41B
Context32K
Q4_K_M1.5 GB
AR
Arcee ai.Arcee Blitz
Arcee · DevQuasar-8
Params23.6B
Context32K
Q4_K_M14.3 GB
CA
Nitral AI.Captain Eris Violet GRPO v0.420
Captain · DevQuasar-8
Params12.2B
Context1000K
Q4_K_M7.5 GB
PE
Perplexity Ai.R1 1776
DevQuasar-8
Params671B
Context160K
Smallest244.0 GB
OP
open neo.Kyro n1 7B
Open · DevQuasar-8
Params7.62B
Context32K
Q4_K_M4.7 GB
QW
Qwen.Qwen2 Math 7B
Qwen · DevQuasar-8
Params7.62B
Context4K
Q4_K_M4.7 GB
LL
Llama 3.1 Minitron 4B Depth Base
Llama · DevQuasar-8
Params4.54B
Context128K
Q4_K_M2.8 GB
VI
Virtuoso Medium
Virtuoso · DevQuasar-8
Params32.8B
Context128K
Q4_K_M19.8 GB
QW
Qwen.Qwen2 Math 1.5B
Qwen · DevQuasar-8
Params1.54B
Context4K
Q4_K_M1.0 GB
KI
arcee ai.KidRails
Kidrails · DevQuasar-8
Params8.03B
Context128K
Q4_K_M4.9 GB
OL
amd.AMD OLMo 1B
OLMo · DevQuasar-8
Params1.18B
Context2K
Q4_K_M0.7 GB