Gemma 4 NVFP4 Quantization Released
kalyan_kpl · x · 2026-07-15
Unsloth released the NVFP4 quantized version of Gemma 4, focusing on faster GPU inference and lower VRAM usage.
- The 12B version can run on 11GB VRAM
- The 26B-A4B achieves 13K tok/s on the B200
- Official claims show a 1.5× inference speedup compared to existing solutions
- The focus is on more accurate 4-bit inference optimization tailored for the Blackwell architecture
The post also includes blog and model links, representing a concrete and usable inference optimization update.
Related event: Unsloth Releases NVFP4 Quantized Gemma 4 for Faster Inference(2 posts)→
More from Infra
- Oracle Q1: Triple-digit cloud infrastructure growth as AI demand booms — DavidLinthicum · 2026-09-11
- SF Compute founder: buying compute is 'an absolutely awful experience' right now — IgorCarron · 2026-09-11
- SmolVM open-sources persistent computer infrastructure for agents that outlive chat sessions — aniketmaurya · 2026-09-11
- PyTorch Day Korea 2026 launches first offline conf, CFP closes Sept 13 — PyTorch · 2026-09-11
- Local LLM server dilemma: 4x CMP-170HX (price up 53% in 20 days) vs Mac Studio M5 Ultra — rumboll · 2026-09-11
- llama.cpp lands Flash Attention tuning for RDNA4, big prefill gains on AMD — pmttyji · 2026-09-11