Tencent Hunyuan releases GGUF quantizations of Hy-Memory-30B-A3B for llama.cpp
Tencent Hunyuan published a GGUF repository for Hy-Memory-30B-A3B, a roughly 30B-parameter long-term-memory writer model with about 3B active parameters, aimed at local inference through llama.cpp. Three quantization levels are offered: Q6_K imatrix at 24.71 GB, Q8_0 at 31.99 GB and Q4_K_M imatrix at 18.24 GB, all under Apache-2.0. The model card reports LoCoMo Judge scores of 58.78% (154/262) for Q6_K, 57.63% for Q8_0 and 56.49% for Q4_K_M on a fixed 20% LoCoMo split using the Mem0 2.0.19 harness, with gpt-5.6-sol as answer and judge model; these figures are self-reported by the publisher and not independently replicated.
The quantizations let the memory-writer model run locally via llama.cpp, and Tencent says it can replace the general-purpose LLM inside memory frameworks such as Mem0, MemOS and Hy-Memory.
tencent/Hy-Memory-30B-A3B-GGUF Text Generation • 30B • Updated 9 days ago • 30.6k • 27
language:
- en
- zh pipeline_tag: text-generation library_name: transformers license: apache-2.0 base_model: tencent/Hy-Memory-30B-A3B tags:
- gguf
- llama.cpp
#Tencent Hunyuan#Hy-Memory-30B-A3B#llama.cpp#Mem0#MemOS#EverMemOS#Claude Opus 5#DeepSeek V4.1 Flash#Qwen3-embedding-8b