MiniMax-M2.7

Model · Text generation

Hy3-Razor-226B-A18B-E144of192

Mingyang Song

Hy3 with a quarter of its routed experts removed by RAZOR, a training-free expert pruning method. Every MoE layer keeps 144 of its original 192 routed experts. No gradient updates or recovery training were applied: the retained weights are the base model's own weights. Pruning touches only the routed expert pool. Attention, shared experts, the embedding and the LM head are untouched, so the compute per token drops only by the share of expert FLOPs that the removed experts would have contributed. The other budget is Requires a Transformers build containing the native hyv3 implementation. Weights are bfloat16. RAZOR asks whether the surviving computation can replace an expert's function…

Model · Text generation

Qwen3-235B-A22B-Thinking-2507

Zachary Howard

Over the past three months, we have continued to scale the thinking capability of Qwen3-235B-A22B, improving both the quality and depth of reasoning. We are pleased to introduce Qwen3-235B-A22B-Thinking-2507, featuring the following key enhancements: - Significantly improved performance on reasoning tasks, including logical reasoning, mathematics, science, coding, and academic benchmarks that typically require human expertise — achieving state-of-the-art results among open-source thinking models. - Markedly better general capabilities, such as instruction following, tool usage, text generation, and alignment with human preferences. - Enhanced 256K long-context understanding capabilities.…

Model · Text generation

DeepSeek-V4.1-Flash-EXL3-3bpw-2x-RTX-PRO-6000

Diffbot

DeepSeek-V4.1-Flash, ready to serve on two RTX PRO 6000 Blackwell cards (sm120, 96 GB each) with vLLM at tensor-parallel 2. The routed experts are - int4 Engram tables; - a 3-bit DSpark drafter; - a serving stack that keeps 30% of the routed experts (the ones agentic coding uses least) in pinned host RAM and runs them next to the VRAM experts; - a decode-once prefill kernel for the 3-bit experts. The recipe/ folder has the image build, the sm120 patches, the MoE kernel, and the serving, benchmark, KL and quantization scripts. We measured KL against the original model with uses the original model's top-512 logprobs on three corpora, 49,152 scored positions each. The neutral corpus is…

Goal: oQ4e speed and memory footprint, oQ5e-or-better quality reaching toward oQ6e. Runs at ~73–75 GB resident with ~82→66 tok/s decode on a 128 GB Apple Silicon host — the speed/RAM economics of a 4-bit build, at an accuracy tier equal to or above uniform oQ5e. How: a mixed-precision MLX build of Qwen3.8-Flash-Next, assembled by component-wise byte-copy from Jundot's native oQ quantizations — zero re-quantization in the entire package. Every tensor is byte-identical to its source, so quality is traceable, not re-derived. Uniform-bit quantization pays accuracy where it isn't needed (middle layers) and loses it where it hurts (first/last layers, n-gram table, attention). A Data-Free…

Model · Text generation

DeepSeek-V4-Flash

DeepSeek

We present a preview version of DeepSeek-V4 series, including two strong Mixture-of-Experts (MoE) language models — DeepSeek-V4-Pro with 1.6T parameters (49B activated) and DeepSeek-V4-Flash with 284B parameters (13B activated) — both supporting a context length of one million tokens. DeepSeek-V4 series incorporate several key upgrades in architecture and optimization: 1. Hybrid Attention Architecture: We design a hybrid attention mechanism combining Compressed Sparse Attention (CSA) and Heavily Compressed Attention (HCA) to dramatically improve long-context efficiency. In the 1M-token context setting, DeepSeek-V4-Pro requires only 27% of single-token inference FLOPs and 10% of KV cache…

Model · Text generation

DeepSeek-V4-Flash-DSpark

DeepSeek

Note: DeepSeek-V4-Flash-DSpark is not a new model. It is the same checkpoint with an additional speculative decoding module attached. A minimal inference example is available in the inference folder. For more details, refer to: https://github.com/deepseek-ai/DeepSpec We present a preview version of DeepSeek-V4 series, including two strong Mixture-of-Experts (MoE) language models — DeepSeek-V4-Pro with 1.6T parameters (49B activated) and DeepSeek-V4-Flash with 284B parameters (13B activated) — both supporting a context length of one million tokens. DeepSeek-V4 series incorporate several key upgrades in architecture and optimization: 1. Hybrid Attention Architecture: We design a hybrid…