Siarhiej Siamaška
ssvb
AI & ML interests
None yet
Recent Activity
new activity 3 days ago
openbmb/MiniCPM-V-4.7-35B-A3B-gguf:2x slower than qwen 3.6 35b A3BOrganizations
None yet
2x slower than qwen 3.6 35b A3B
4
#12 opened 4 days ago
by
ZeroWw
Scion Flash-Next vs Qwen3.8-Flash-Next GSQ-RCO: a 30-task A/B
2
#71 opened 7 days ago
by
SkyIsNotGreen
Don't waste your time with this model
👍 12
8
#31 opened 15 days ago
by
SamirGFX
Updated chat template
🔥👍 6
10
#15 opened 18 days ago
by
anm2211
base64 decoding test on 150 chunks
10
#103 opened 20 days ago
by
KottCh
Request to bonsai
👀👍 7
8
#95 opened 27 days ago
by
Banaxi-Tech
Has anyone compared Ternary Bonsai 2 model quality retention versus ISTA-DASLab's GSQ-RCO?
👍 1
11
#99 opened 24 days ago
by
ssvb
Lookahead Expert Scheduling (LES) for streaming from SSD drive (MoE-SSD)
👍 1
16
#15 opened 25 days ago
by
ssvb
Suggesting non-Qwen bases for the next generation of Bonsai (with a focus on code quality)
🔥 2
2
#2 opened 22 days ago
by
aliman32
thinking hard-disabled for llama.cpp GGUF
4
#7 opened 20 days ago
by
engrtipusultan
MiniCPM V-4.7-35B-A3B, VRAM Requirements
4
#16 opened 21 days ago
by
mzubairtahir000714
Ternary-Bonsai-2-27B-PQ2_0: Comprehensive Model Evaluation and User Review
1
#101 opened 22 days ago
by
lscdev2
Speculative Drafters for Ternary-Bonsai-2-27B (11~13 tok/s on Apple Silicon M3)
🔥 1
3
#100 opened 23 days ago
by
NOhhh
Lookahead Expert Scheduling (LES) for streaming from SSD drive (MoE-SSD)
👍 1
16
#15 opened 25 days ago
by
ssvb
Has anyone compared Ternary Bonsai 2 model quality retention versus ISTA-DASLab's GSQ-RCO?
👍 1
11
#99 opened 24 days ago
by
ssvb
Request to bonsai
👀👍 7
8
#95 opened 27 days ago
by
Banaxi-Tech
Request to bonsai
👀👍 7
8
#95 opened 27 days ago
by
Banaxi-Tech