(1)
SmolLM3 is a 3.1B model for efficient on-device use, with strong performance in chat
1y
100K+
9
Google’s latest Gemma, small yet strong for chat and generation
5m
2.4K
Q4_K_M GGUF of a MedGemma health-chat fine-tune for local, private clinical AI prototyping.
3m
36
Step-3.5-Flash Q3_K_M GGUF for Docker Model Runner (chat)
12d
156
MiniMax-M2.5 UD-Q2_K_XL GGUF for Docker Model Runner (chat)
12d
129
DeepSeek-V4-Flash UD-IQ3_XXS GGUF for Docker Model Runner (chat)
14d
157
EuroLLM-22B-Instruct Q4_K_M GGUF for Docker Model Runner (chat)
13d
48
Qwen2.5-32B-Instruct Q4_K_M GGUF for Docker Model Runner (chat)
9d
43
Olmo 3.1 32B Think Q4_K_M GGUF for Docker Model Runner (chat)
13d
52
Hermes 4.3 36B Q4_K_M GGUF for Docker Model Runner (chat)
13d
40
KAT-Coder-V2.5-Dev Q4_K_M GGUF for Docker Model Runner (chat)
12d
46
Qwen-AgentWorld-35B-A3B UD-Q4_K_M GGUF for Docker Model Runner (chat)
12d
53
Huihui Qwen3.8-27B abliterated UD-DW-Q4_K_M GGUF for Docker Model Runner (chat)
13d
65
GLM-Z1-32B-0414 Q4_K_M GGUF for Docker Model Runner (chat)
11d
42
DeepSeek-R1-Distill-Qwen-32B Q4_K_M GGUF for Docker Model Runner (chat)
14d
50
LFM2.5-24B-A2B Q4_K_M GGUF for Docker Model Runner (chat)
7d
32
GLM-4-32B-0414 Q4_K_M GGUF for Docker Model Runner (chat)
3d
38
Qwen 3.6 35B A3B GGUF quantizations from Unsloth Studio with the Nail chat template.
2m
65
Mellum2-12B-A2.5B-Instruct Q8_0 GGUF for Docker Model Runner (chat)
13d
36
Olmo 3.1 32B Instruct Q4_K_M GGUF for Docker Model Runner (chat)
3d
34
North Mini Code 1.0 UD-Q4_K_M GGUF for Docker Model Runner (chat)
13d
34
ERNIE-4.5-21B-A3B-Thinking Q4_K_M GGUF for Docker Model Runner (chat)
12d
34
DeepSeek-Coder-V2-Lite-Instruct Q4_K_M GGUF for Docker Model Runner (chat)
11d
29