nvidia/Riva-Translate-4B-Instruct-v2
Text Generation • 4B • Updated • 1.24k • 15
🔄 In a Training Loop
Zdenek Slavik
slavikz
·
AI & ML interests
None yet
Recent Activity
liked a model 7 days ago
nvidia/Riva-Translate-4B-Instruct-v2 updated a model 13 days ago
inferRouter/qwen3-asr-cs-1.7bOrganizations
liked a
model 7 days ago
reacted to julien-c's post with 🤗 7 days ago
Post
3981
who's working on an NVFP4 version of Kimi-K3?
- 4 replies
updated a
model 13 days ago
updated a
model about 1 month ago
updated a
collection about 1 month ago
published 2
models about 1 month ago
Multilingual version planned?
16
#2 opened 7 months ago
by 
fosple
liked a
model 3 months ago
updated a
model 3 months ago
published a
model 3 months ago
updated a
model 3 months ago
reacted to eaddario's post with 🚀 3 months ago
Post
3318
Experimental global target bits‑per‑weight quantization of Qwen/Qwen3.6-27B and Qwen/Qwen3.6-35B-A3B.
Unlike standard llama.cpp quantizations that rely on fixed type heuristics (e.g., Q4_K_M), the Target BPW approach optimizes per-tensor precision where it matters the most, and produces high quality models that meet a precise global file 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 models' cards.
eaddario/Qwen3.6-27B-GGUF
eaddario/Qwen3.6-35B-A3B-GGUF
Unlike standard llama.cpp quantizations that rely on fixed type heuristics (e.g., Q4_K_M), the Target BPW approach optimizes per-tensor precision where it matters the most, and produces high quality models that meet a precise global file 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 models' cards.
eaddario/Qwen3.6-27B-GGUF
eaddario/Qwen3.6-35B-A3B-GGUF
updated a
model 3 months ago
published a
model 3 months ago
updated a
model 3 months ago
published 2
models 3 months ago
Why is this 4bit version has a 32.7 GB size?
➕ 3
20
#3 opened 4 months ago
by 
alexcardo