https://huggingface.co/tencent/Hy3. can you create a gguf for apple m5 max of this ?
#17 opened 19 days ago
by
RobZombAI
Running with recently merged llama.cpp PR
π 6
6
#16 opened 26 days ago
by
ubergarm
New dspark variants
β€οΈ 8
#15 opened 29 days ago
by
sm54
DSv4 PRO download show 400 error
#14 opened 29 days ago
by
imweijh
code
1
#13 opened about 1 month ago
by
erichartford
TemporalMesh Transformer: 29.4 PPL at 48% compute β beats Mamba, new open-source architecture
#12 opened about 2 months ago
by
vigneshwar234
A quantization model with a total size of less than 107GB should be well-suited for deployment on a 128GB Mac.
#11 opened 2 months ago
by
mimeng1990
Is the IQ2XXS better than qwen3.6 27b in general reasoning and agentic coding?
ππ 4
1
#10 opened 2 months ago
by
rumcs
I can't download the pro, it gives a 400 error
π 2
1
#9 opened 2 months ago
by
segmond
RPC server possible?
#8 opened 2 months ago
by
x-polyglot-x
Suggestion: Add IQ3 variants.
π 2
4
#7 opened 2 months ago
by
tarruda
Suggest renaming files per GGUF naming convention
β 3
1
#6 opened 2 months ago
by
mishig
Update README.md
#5 opened 3 months ago
by
arpitjain96
Can it be used?
5
#1 opened 3 months ago
by
X-AI-GT