GGUF models by bunnycore

161 GGUF models quantized by bunnycore on Hugging Face. Sizes run from 1M to 14.7B parameters. The longest trained context is 1024K tokens.

Most downloadedNewestLargestLongest contextSmallest
LF
LMF 2.5 2B Code
Lfm · bunnycore
Params2.7B
Context128K
Smallest1.9 GB
Coding
MI
SuperMiniCPM5 2B Qween
MiniCPM · bunnycore
Params2.52B
Context128K
Smallest2.7 GB
ReasoningTool use
MI
MiniCPM5 2B Code
MiniCPM · bunnycore
Params2.52B
Context128K
Smallest2.7 GB
CodingReasoningTool use
MI
MiniCPM5 2B Claude Distill
MiniCPM · bunnycore
Params2.52B
Context128K
Smallest2.1 GB
ReasoningTool use
MI
MiniCPM5 2B Super
MiniCPM · bunnycore
Params2.52B
Context128K
Smallest2.7 GB
ReasoningTool use
MI
MiniCPM5 2B Code lora
MiniCPM · bunnycore
Params50M
Context—
Smallest0.1 GB
GGUF
QW
LMF 2.5 2.6B Qwen3.8 Distilled
Qwen · bunnycore
Params1M
Context—
Smallest0.0 GB
GGUF
GE
Dolphin 2.9.4 Gemma2 2b
Gemma · bunnycore
Params2.61B
Context8K
Q4_K_M1.7 GB
GGUF
PH
Phi 3.5 Hyper Mix IQ4 XS
Phi · bunnycore
Params3.82B
Context128K
Smallest2.1 GB
GGUF
MI
MiniCPM5 2B Super Lora
MiniCPM · bunnycore
Params50M
Context—
Smallest0.1 GB
GGUF
MI
MiniCPM5 2B Qwen3.8 Distill
MiniCPM · bunnycore
Params50M
Context—
Smallest0.1 GB
GGUF
GE
Gemma4 E2B Qwen3.8 Distilled
Gemma · bunnycore
Params25M
Context—
Smallest0.0 GB
GGUF
QW
Qwen2.5 3B RP Mix Q5 K M
Qwen · bunnycore
Params3.4B
Context32K
Smallest2.4 GB
RoleplayTool use
MI
MiniCPM5 2B RP Lora
MiniCPM · bunnycore
Params25M
Context—
Smallest0.1 GB
GGUF
QW
Qwen 2.5 7b TitanFusion v2 IQ4 NL
Qwen · bunnycore
Params7.62B
Context32K
Smallest4.4 GB
GGUF
LL
LLama 3.1 8b Ultra Max Pro Q5 K M
Llama · bunnycore
Params8.03B
Context128K
Smallest5.7 GB
GGUF
QW
Qwen 2.5 3b RP IQ4 XS
Qwen · bunnycore
Params3.4B
Context32K
Smallest1.9 GB
RoleplayTool use
KI
LMF2.4 2.6B Kimi
Kimi · bunnycore
Params2M
Context—
Smallest0.0 GB
GGUF
LF
LFM2.5 2.6B RP V2
Lfm · bunnycore
Params2.7B
Context128K
Smallest1.9 GB
ReasoningRoleplayTool use
GE
Gemma4 E2B Coding Distill
Gemma · bunnycore
Params101M
Context—
Smallest0.2 GB
GGUF
LF
LMF 2.5 2.6B RP Lora
Lfm · bunnycore
Params1M
Context—
Smallest0.0 GB
GGUF
LL
LLama 3.1 8B Matrix Q5 K M
Llama · bunnycore
Params8.03B
Context128K
Smallest5.7 GB
GGUF
QW
Qwen3 4B Mixture
Qwen · bunnycore
Params3.64B
Context40K
Smallest3.0 GB
ReasoningTool use
CA
Calme 7B Instruct v0.9 Q5 K S
Calme · bunnycore
Params7.24B
Context32K
Smallest5.0 GB
GGUF
LF
LMF 2.5 2B Code Lora
Lfm · bunnycore
Params1M
Context—
Smallest0.0 GB
GGUF
ST
Starling LM 7B beta laser dpo Q5 K M
Starling · bunnycore
Params7.24B
Context8K
Smallest5.1 GB
GGUF
LL
Llama 3.1 8B TitanFusion v2 Q4 K M
Llama · bunnycore
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
MI
MiniCPM5 2B Claude Distill Lora
MiniCPM · bunnycore
Params50M
Context—
Smallest0.1 GB
GGUF
LF
LMF2.5 2.6B Hunter
Lfm · bunnycore
Params5M
Context—
Smallest0.0 GB
GGUF
GE
Gemma4 E2B Agent
Gemma · bunnycore
Params51M
Context—
Smallest0.1 GB
GGUF

About bunnycore on Hugging Face

bunnycore has published 161 GGUF models that ggufmodels.com tracks, across families such as Llama, Qwen and Gemma. The most downloaded are LMF 2.5 2B Code, SuperMiniCPM5 2B Qween and MiniCPM5 2B Code.

The quants bunnycore publishes most often are Q5_K_M (57), IQ4_NL (27), Q4_K_M (24) and Q8_0 (15). Their Q4_K_M files range from 1.7 to 8.9 GB. Parameter counts run from 1M to 14.7B, and the longest trained context window is 1024K tokens.

Frequently asked questions

What GGUF models has bunnycore published?

161 models are listed here, mainly from the Llama, Qwen and Gemma families. The most downloaded is LMF 2.5 2B Code.

Which quants does bunnycore publish?

The most common are Q5_K_M (57 models), IQ4_NL (27 models), Q4_K_M (24 models) and Q8_0 (15 models).

Keep browsing