Jean-Marc Reynaud
lefromage
AI & ML interests
None yet
Recent Activity
liked a model 4 days ago
EverMind-AI/MSA-4B upvoted a collection 11 days ago
Gemma 4 liked a model 11 days ago
ggml-org/gemma-4-31B-it-GGUFOrganizations
None yet
Please restore the TQ1_0 model
1
#17 opened about 1 month ago
by
lefromage
please restore the TQ1_0 model
ππ 3
4
#19 opened about 1 month ago
by
lefromage
MXFP4 difference
3
#7 opened 4 months ago
by
Ubong0
IQ4_XS Please
3
#6 opened 5 months ago
by
lingyezhixing
lefromage/Qwen3-Next-80B-A3B-Instruct-GGUF
4
#5738 opened 6 months ago
by
lefromage
i just created merged pr for fast and accurate one
π 2
1
#5 opened 5 months ago
by
gopi87
CUDA acceleration not working (GPU utilization ~0% on dual A6000)
5
#4 opened 6 months ago
by
charlene22
Testing report on Intel Xeon W5-3425
π 1
3
#1 opened 6 months ago
by
SlavikF
Q6 is better then Q8
4
#2 opened 6 months ago
by
gopi87
LM Studio - Failed to load the model
3
#3 opened 6 months ago
by
mknez78
Error on building
2
#1 opened 6 months ago
by
Ndrewpj
gguf not llama.cpp compatible yet
π 1
3
#2 opened 12 months ago
by
lefromage
configuration_bitnet.py missing
πβ 12
15
#4 opened 12 months ago
by
lefromage
llama.cpp llama-cli cannot load : unknown pre-tokenizer type: 'trillion'
3
#1 opened about 1 year ago
by
lefromage
all the scores are NaN
7
#4 opened about 1 year ago
by
lefromage
all the scores are NaN
7
#4 opened about 1 year ago
by
lefromage