Symbiotic-Beta

Bonsai 2 27B by Prism ML, repacked for vLLM. Unofficial; not affiliated with Prism ML. It needs the prismternary vLLM plugin from fraserprice/bonsai-vllm, which has the run command, kernels and throughput numbers: Built and tested for the RTX PRO 6000 Blackwell only; other NVIDIA GPUs are untested. Problems: open an issue. - The ternary weights of the MLX pack, bit for bit: the same 2-bit codes and FP16 group scales (g128), in the same Hadamard-rotated basis. MLX's redundant per-group biases (-scale) are dropped, and the rotation signs move into config.json. - The embedding table is dequantized to BF16. - Norms and the linear-attention state path are Prism ML's own tensors from the MLX…

Model · Text generation

granite-4.2-3b-MXFP4A16-GPTQ

David Reedy

An experimental MXFP4 quantization of ibm-granite/granite-4.2-3b, made with GPTQ calibration instead of the usual data-free rounding, and provided in two formats with identical weights. It's published as a data point, not as the recommended build. For most users, the Q4KM GGUF or GPTQ int4 build is the better choice. Format: OCP MX — E2M1 (FP4) weights, groupsize=32, one UE8M0 shared scale per group; weights only, activations stay 16-bit. Embeddings, norms and lmhead are unquantized. MXFP4 is usually produced data-free, by rounding weights straight to FP4 with no calibration data. llm-compressor ships an MXFP4A16 scheme, but every example we found pairs GPTQModifier with integer schemes…

Model · Text generation

granite-4.2-3b-W4A16-GPTQ-gs32

David Reedy

A 4-bit weight-only GPTQ quantization of ibm-granite/granite-4.2-3b, saved in compressed-tensors format for vLLM. On an AMD Radeon Pro V620 (RDNA2), vLLM served it at 65 tok/s single-sequence and ~1,000 tok/s aggregate at 16 concurrent sequences. llm-compressor GPTQModifier: - int4, symmetric, weight-only (activations stay 16-bit) - groupsize=32, actorder="weight" - lmhead left unquantized 512 samples, maxseqlength=512 The tuning mattered. With the default W4A16 preset (groupsize=128), the same pipeline scored 0.153 mean KLD. Moving to groupsize=32 with actorder="weight" cut that by about 28%, for roughly 0.2 GB more disk. For comparison, an AWQ build (W4A16 asymmetric, groupsize=128) from…

Emendator is a byt5-xl model finetuned to correct OCR artifacts in Latin text. This model cannot provide completely faithful reconstruction for all orthographies - on a large scale, it will shift the distribution of tokens towards that which it has been trained on. This is to say: Emendator will take editorial liberties with your data. As such, use it only in circumstances when the primary concern is only to recover intelligible Latin, not to recover intelligible Latin of a particular style. The model is intended to be used on segments of 250 characters. Anything else will compromise performance. Original: "atque optimo viro, peterem; superavi tamen dignitate Catilinam, gratia Galbam. Quod…

Model · Text generation

PowerMoE-3b

IBM Research

PowerMoE-3B is a 3B sparse Mixture-of-Experts (sMoE) language model trained with the Power learning rate scheduler. It sparsely activates 800M parameters for each token. It is trained on a mix of open-source and proprietary datasets. PowerMoE-3B has shown promising results compared to other dense models with 2x activate parameters across various benchmarks, including natural language multi-choices, code generation, and math reasoning. This is a simple example of how to use PowerMoE-3b model.

Model · Text generation

MarinSkyRL-Open-MOPD-SmolLM3-3B-step-32

Open Athena

This is a MarinSkyRL-native Open-MOPD student after 32 optimizer steps. It starts from the authors' mixed-domain SFT checkpoint. Student responses were scored by the authors' math, code, and instruction-following RL teachers, routed by domain. The objective uses the student's selected top-16 token IDs and a clipped policy surrogate. This is an early checkpoint, not the authors' step-200 final model. The checkpoint is an unquantized, six-file Hugging Face export of the durable MarinSkyRL globalstep32 FSDP2 checkpoint. The policy export was used for the independent step-32 evaluation. The export's model.safetensors SHA-256 is bb7326640142069bc2e1fba5f54f15e0cccb1ff861f34f318b372eaab7abaf4b.…