incoai/GLM-5.3-Flash-DFlash2
1mo
74
- Collected
What it costs to run this
1.2
| Precision | Needs | Cheapest that fits |
|---|---|---|
| 16-bit | 3.2 | GTX 1660 S |
| 8-bit | 1.6 | GTX 1660 S |
| 4-bit | 0.8 | GTX 1660 S |
Weights plus attention cache, with 15% added for activations and allocator overhead. Everything here is arithmetic — we do not measure speed, so we do not rank chips by it. See all GPU prices
New text-generation model. Tags: qwen3, dflash, dflash2, speculative-decoding, block-diffusion, draft-model, sglang, text-generation
overfeed.news indexes and links. We publish a short excerpt — the full article stays at Hugging Face New Models.
More from Hugging Face New Models
Log in to follow this source
JetBrains/Mellum2.1-12B-A2.5B-Thinking
New text-generation model. Tags: mellum, text-generation, conversational, en, arxiv:2605.31268, base_model:JetBrains/Mellum2-12B-A2.5B-Base, base_model:finetune:JetBrains/Mellum2-12B-A2.5B-Base, license:apache-2.0
AtomicChat/Qwen-Image-2.1-Turbo-Uncensored-GGUF
New text-to-image model. Tags: gguf, atomic-chat, qwen, qwen-image, qwen3-vl, text-encoder, stable-diffusion.cpp, abliteration
speridlabs/iris-3b
New text-to-image model. Tags: pytorch, text-to-image, diffusion, pixel-space, flow-matching, general-vision-learner, vision-foundation-model, depth-estimation
perplexity-ai/pplx-decider-v1.1-27b
New text-classification model. Tags: pytorch, qwen3_5, classification, multimodal, custom-code, decider, decision-model, text-classification