GGUF Fuzzy
Collection
9 items • Updated
William J. Marshall
fuzzy-mittenz
AI & ML interests
None yet
Recent Activity
updated a collection 2 days ago
GGUF Fuzzy updated a collection 3 days ago
SwarmModels liked a model 3 days ago
aifeifei798/Heretic-Scalpel-E2BOrganizations
updated a
collection 2 days ago
updated a
collection 3 days ago
liked a
model 3 days ago
updated a
collection 3 days ago
liked 2
models 3 days ago
liked a
model 4 days ago
liked a
model 6 days ago
updated a
Space 7 days ago
liked a
model 10 days ago
liked a
model 11 days ago
reacted to eaddario's post with 🤯 13 days ago
Post
131
Experimental global target bits‑per‑weight quantization of XHToken/Spark-X2.5-1.7B and XHToken/Spark-X2.5-4B.
Unlike standard llama.cpp quantization that rely on fixed type heuristics (e.g., Q4_K_M), the Target BPW approach automatically optimizes per-tensor precision where it matters the most, and produces high quality models that meet a precise global size target.
Key Advantages:
- VRAM Maximization: Can generate high quality models sized exactly to fit hardware constraints (e.g., fitting the model into exactly 24GB VRAM).
- Data-Driven Precision: Quantization mix is determined by actual weight error sensitivity rather than hardcoded rules, often yielding better PPL/KLD size trade-offs.
Full benchmarks (PPL, KLD, ARC, GPQA, MMLU, etc.) and methodology in the model's card.
eaddario/Spark-X2.5-1.7B-GGUF
eaddario/Spark-X2.5-4B-GGUF
Unlike standard llama.cpp quantization that rely on fixed type heuristics (e.g., Q4_K_M), the Target BPW approach automatically optimizes per-tensor precision where it matters the most, and produces high quality models that meet a precise global size target.
Key Advantages:
- VRAM Maximization: Can generate high quality models sized exactly to fit hardware constraints (e.g., fitting the model into exactly 24GB VRAM).
- Data-Driven Precision: Quantization mix is determined by actual weight error sensitivity rather than hardcoded rules, often yielding better PPL/KLD size trade-offs.
Full benchmarks (PPL, KLD, ARC, GPQA, MMLU, etc.) and methodology in the model's card.
eaddario/Spark-X2.5-1.7B-GGUF
eaddario/Spark-X2.5-4B-GGUF
liked 2
models 16 days ago
published a
model 16 days ago
updated a
model 16 days ago
updated a
model 17 days ago
published a
model 17 days ago
updated 2
collections 17 days ago