John's picture

John

cmp-nct

·

https://github.com/cmp-nct/ggllm.cpp

cmp-nct

AI & ML interests

None yet

Recent Activity

updated a model 1 day ago

cmp-nct/acestep-5Hz-lm-4B-GGUF

liked a model 7 days ago

ACE-Step/acestep-v15-base

new activity 25 days ago

zai-org/GLM-4.7-Flash:llama.cpp inference - 20 times (!) slower than OSS 20 on a RTX 5090

View all activity

Organizations

New activity in zai-org/GLM-4.7-Flash 25 days ago

llama.cpp inference - 20 times (!) slower than OSS 20 on a RTX 5090

#12 opened 25 days ago by

New activity in Alibaba-Apsara/DASD-30B-A3B-Thinking-Preview 28 days ago

Interesting model - how to control reasoning length?

#2 opened 28 days ago by

New activity in unsloth/Nemotron-3-Nano-30B-A3B-GGUF about 2 months ago

Should UD-Q6_K_XL identical to Q6_K.gguf?

#1 opened about 2 months ago by

Quantizations below 4 bit are bad

#4 opened about 2 months ago by

New activity in noctrex/Nemotron-3-Nano-30B-A3B-MXFP4_MOE-GGUF about 2 months ago

MXFP4

#1 opened about 2 months ago by

New activity in nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 about 2 months ago

Good model but it is very flawed in recalling input

#5 opened about 2 months ago by

New activity in moonshotai/Kimi-Linear-48B-A3B-Instruct 3 months ago

No space to test it, not on open router, are there obstacles ?

#9 opened 3 months ago by

New activity in kernels-community/triton_kernels 6 months ago

Kernel assertion errors on 5090 using generation with MXfp4 (gpt-oss) - (stable on 4090)

#1 opened 6 months ago by

New activity in unsloth/gpt-oss-20b-bnb-4bit 6 months ago

Creating quantization

#4 opened 6 months ago by

New activity in LGAI-EXAONE/EXAONE-4.0-32B 7 months ago

This model is not much better than qwen3 32b for writing code

#4 opened 7 months ago by

New activity in SebastianBodza/Kartoffelbox-v0.1 7 months ago

Wan't to share my Training-Set

#4 opened 8 months ago by

Very good results

#5 opened 7 months ago by

New activity in nari-labs/Dia-1.6B 10 months ago

Multiple languages support

#19 opened 10 months ago by

New activity in Qwen/Qwen3-0.6B 10 months ago

Very coherent for the size, though it is also adamant in defending its wrong conclusions and false knowledge

#5 opened 10 months ago by

New activity in NousResearch/Minos-v1 10 months ago

Interesting idea, what about multi lingual prompts ?

#7 opened 10 months ago by

New activity in GSAI-ML/LLaDA-8B-Instruct 11 months ago

Gguf?

#2 opened 12 months ago by

AlgorithmicKing

New activity in openbmb/MiniCPM-o-2_6 about 1 year ago

Safety

#21 opened about 1 year ago by

New activity in xtuner/llava-phi-3-mini-gguf over 1 year ago

Modl showing up as Llama instead of phi3 in LMstudio

#1 opened almost 2 years ago by

New activity in openbmb/MiniCPM-Llama3-V-2_5 over 1 year ago

gguf / llama.cpp support

#45 opened over 1 year ago by

Using gguf format

#1 opened over 1 year ago by