Thireus PRO
Thireus
AI & ML interests
None yet
Recent Activity
updated a model about 1 hour ago
Thireus/GLM-5.1-THIREUS-Q4_K-SPECIAL_SPLIT updated a model about 2 hours ago
Thireus/GLM-5.1-THIREUS-IQ3_K_R4-SPECIAL_SPLIT updated a model about 2 hours ago
Thireus/GLM-5.1-THIREUS-IQ3_KT-SPECIAL_SPLITOrganizations
None yet
Check out Thireus GGUF-Tool-Suite quants!
β€οΈπ€ 5
8
#13 opened 11 days ago
by
ubergarm
Seeing GGUF-Tool-Suite Outputs in the Wild β Thank You!
π 1
#1 opened 4 days ago
by
Thireus
Testing Q4_0
π₯ 1
2
#2 opened about 2 months ago
by
shewin
Found block with mismatching importance/model weights
1
#11 opened about 1 month ago
by
Thireus
Imatrix from BF16 ?
π 1
2
#6 opened 5 months ago
by
bobchenyx
Should ffn_down experts be quantized the same as ffn_up/ffn_gate?
5
#2 opened 6 months ago
by
Downtown-Case
Any chance for an IQ3_K?
π 2
34
#6 opened 8 months ago
by
original-el8
llama.cpp/tools/mtmd/mtmd.cpp - Missing PROJECTOR_TYPE_QWEN3VL
1
#1 opened 6 months ago
by
Thireus
imatrix coming soon? π«£
π€ 1
8
#1 opened 7 months ago
by
Thireus
quant req: 256 GB RAM + 96 GB VRAM
π 1
28
#1 opened 8 months ago
by
whoisjeremylam
Good job
56
#2 opened 8 months ago
by
huccjj
Not working as expected?
1
#1 opened 8 months ago
by
Thireus
what is this ?
1
#1 opened 8 months ago
by
gopi87
qwen3 2507 test
12
#6 opened 9 months ago
by
shewin
imatrix-eaddario-combined-all-medium-Qwen3-235B-A22B-Instruct-2507-BF16.dat ?
3
#7 opened 9 months ago
by
Thireus
Is there a chance to get the AWQ or DWQ model? Mac Studio (512GB) has a 3-bit honey point.
π 1
5
#1 opened 11 months ago
by
zletpm
DeepSeek-R1-256x21B-0528-BF16 GGUF?
π 1
5
#12 opened 10 months ago
by
Thireus
ONNX version planned?
3
#17 opened 10 months ago
by
Florianoli
Metrics for 110k context size?
1
#4 opened 10 months ago
by
Thireus