GGUF models by sizzlebop
140 GGUF models quantized by sizzlebop on Hugging Face. Sizes run from 27M to 32.8B parameters. The longest trained context is 1024K tokens.
OS
Osmosis Structure 0.6B
Osmosis · sizzlebop
Params596M
Context40K
Smallest0.4 GB
QW
Nemotron Research Reasoning Qwen 1.5B
Qwen · sizzlebop
Params1.78B
Context128K
Q4_K_M1.1 GB
LE
LexiFreak 8B Unleashed
Lexifreak · sizzlebop
Params8.03B
Context8K
Smallest4.7 GB
CU
CursedMatrix 8B v9 Q8 0
Cursedmatrix · sizzlebop
Params8.03B
Context8K
Smallest8.5 GB
GR
Granite 3.3 2b Instruct
Granite · sizzlebop
Params2.53B
Context128K
Smallest2.7 GB
LF
LFM2 VL 450M
Lfm · sizzlebop
Params354M
Context125K
Smallest0.4 GB
HO
Holo1 7B
Holo · sizzlebop
Params7.62B
Context125K
Q4_K_M4.7 GB
QW
openthoughts3 code 100k annotated QwQ 32B sharegpt Q8 0
Qwen · sizzlebop
Params7.62B
Context32K
Smallest8.1 GB
SC
ScholarCopilot v1
Scholarcopilot · sizzlebop
Params7.61B
Context128K
Smallest8.1 GB
HO
Homunculus
Homunculus · sizzlebop
Params12.5B
Context128K
Smallest13.2 GB
QW
Toucan Qwen2.5 7B Instruct v0.1
Qwen · sizzlebop
Params7.62B
Context32K
Smallest4.4 GB
LE
LexiFreak 8B Unleashed
Lexifreak · sizzlebop
Params8.03B
Context8K
Smallest8.5 GB
OR
Orsta 32B 0326
Orsta · sizzlebop
Params32.8B
Context125K
Smallest34.8 GB
GT
Gte Base
Gte · sizzlebop
Params109M
Context512
Smallest0.1 GB
GT
Gte Base
Gte · sizzlebop
Params109M
Context512
Q4_K_M0.1 GB
QW
Qwen3.6 27B Fable 5 Experimental
Qwen · sizzlebop
Params27.3B
Context256K
Smallest29.0 GB
RA
Raptor X2
Raptor · sizzlebop
Params14.8B
Context117K
Smallest15.7 GB
QW
Qwen2.5 7B Open R1 GRPO
Qwen · sizzlebop
Params7.62B
Context32K
Q4_K_M4.7 GB
M1
m 1 Q8 0
sizzlebop
Params7.61B
Context32K
Smallest8.1 GB
M1
m 1 Q6 K
sizzlebop
Params7.61B
Context32K
Smallest6.3 GB