# MathLeap-Qwen-8B by University of Washington Math AI Lab Source: https://savrn.com/models/mathleap-qwen-8b Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve MathLeap-Qwen-8B (7.6B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them. | Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits | | --- | --- | --- | --- | --- | --- | | 16-bit | 15.1 GB | 18.2 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 8-bit | 7.6 GB | 9.1 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 4-bit | 3.8 GB | 4.5 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the [SAVRN Index](https://savrn.com/ai-index/pricing/gpus), read Oct 7, 2026. [MathLeap-Qwen-8B on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/mathleap-qwen-8b/gpus) ## Model Card By University of Washington Math AI Lab, published under apache-2.0, revision ffe9c2a4a1b7. A retrieval-tuned embedding model for mathematical text. Fine-tuned from [Qwen/Qwen3-Embedding-8B](https://savrn.com/models/qwen3-embedding-8b) on mathlib4 concepts via multi-view contrastive learning. On MELD — a benchmark of mathematical statements paired across radically different presentations (e.g., set-theoretic vs. category-theoretic phrasings of the same theorem) — MathLeap-Qwen-8B achieves MMR 0.43, beating its base Qwen3-Embedding-8B (0.32, +0.11) and the retrieval-specialized Octen-Embedding-8B (0.42). | Model | Base | AMP MMR ↑ (specialized prompt) | | --- | --- | --- | | Qwen3-Embedding-8B | — | 0.32 | | Octen-Embedding-8B | Qwen3-8B | 0.42 | | MathLeap-Qwen-8B (this) | Qwen3-8B | 0.43 | ### Usage ``` from huggingface_hub import snapshot_download from sentence_transformers import SentenceTransformer # Download model files from anonymous mirror model_path = snapshot_download( repo_id="anonymous-submission/MathLeap-Qwen-8B", endpoint="https://anonymous-hf.up.railway.app/a/pv25ongyl2qb/ ", ) # Load locally model = SentenceTransformer(model_path) query = "For any natural number n, n + 0 = n." docs = [ "theorem add_zero (n : ℕ) : n + 0 = n := rfl", "theorem mul_zero (n : ℕ) : n * 0 = 0 := rfl", ] q_emb = model.encode([query]) d_emb = model.encode(docs) print(q_emb @ d_emb.T) ``` ### Model details [Read the full model card (750 words)](https://savrn.com/models/mathleap-qwen-8b/card) ## Configuration Architecture Qwen3Model Context length (tokens) 40,960 Layers 36 Hidden size 4,096 Feed-forward size 12,288 Attention heads 32 Key/value heads 8 Head dimension 128 Vocabulary size 151,665 RoPE base 1,000,000 Model type qwen3 ## Identity and Version Repository uw-math-ai/MathLeap-Qwen-8B Publisher University of Washington Math AI Lab Task Sentence similarity Modality Text Library sentence-transformers Parameters 7.6B parameters Languages en Revision ffe9c2a4a1b7777b890044e40a4e4a4d6346ae23 First published 2026-05-25 Last updated 2026-10-01 ## Files and Weights 22 files, 30.3 GB in total. The weights are 7 files totalling 30.3 GB in safetensors. Weights7 files · 30.3 GB Configuration8 files · 34.3 KB Tokenizer4 files · 15.9 MB Documentation1 file · 7.0 KB Other1 file · 2.4 KB Repository1 file · 1.6 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model-00001-of-00007.safetensors | Weights | 5.0 GB | 483abccff841 | | model-00002-of-00007.safetensors | Weights | 4.8 GB | 3db9485404f4 | | model-00003-of-00007.safetensors | Weights | 4.8 GB | c9935c39aed4 | | model-00004-of-00007.safetensors | Weights | 5.0 GB | 4260beb650eb | | model-00005-of-00007.safetensors | Weights | 4.8 GB | dba20754eefb | | model-00006-of-00007.safetensors | Weights | 4.8 GB | b52d3cc979bd | | model-00007-of-00007.safetensors | Weights | 973.2 MB | 6f672adf14db | | 1_Pooling/config.json | Configuration | 313 B | — | | added_tokens.json | Configuration | 605 B | — | | config.json | Configuration | 1.5 KB | — | | config_sentence_transformers.json | Configuration | 375 B | — | | model.safetensors.index.json | Configuration | 30.5 KB | — | | modules.json | Configuration | 349 B | — | | sentence_bert_config.json | Configuration | 57 B | — | | special_tokens_map.json | Configuration | 613 B | — | | README.md | Documentation | 7.0 KB | — | | chat_template.jinja | Other | 2.4 KB | — | | .gitattributes | Repository | 1.6 KB | — | | merges.txt | Tokenizer | 1.7 MB | — | | tokenizer.json | Tokenizer | 11.4 MB | 847b917cf652 | | tokenizer_config.json | Tokenizer | 4.9 KB | — | | vocab.json | Tokenizer | 2.8 MB | — | ## License and Download License apache-2.0 Access Open weights, no gate Download size 30.3 GB [Download from University of Washington Math AI Lab](https://huggingface.co/uw-math-ai/MathLeap-Qwen-8B) Released by University of Washington Math AI Lab through its official repository on Hugging Face. [Read the license](https://www.apache.org/licenses/LICENSE-2.0). ## Built From - Derived from [Qwen/Qwen3-Embedding-8B](https://savrn.com/models/qwen3-embedding-8b) ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 30.3 GB | | 16-bit | 15.1 GB | | 8-bit | 7.6 GB | | 4-bit | 3.8 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Questions About MathLeap-Qwen-8B ### How much GPU memory does MathLeap-Qwen-8B need? About 18.2 GB at 16-bit and 4.5 GB at 4-bit: the weights (7.6B parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run MathLeap-Qwen-8B on? At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists. ### Can I use MathLeap-Qwen-8B commercially? Yes. MathLeap-Qwen-8B is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors. ### What is MathLeap-Qwen-8B's context length? 40,960 tokens, from the maximum position embeddings in its published configuration. ## Similar Models Model · Sentence similarity ### [Octen-Embedding-8B](https://savrn.com/models/octen-embedding-8b) [Octen-Team](https://savrn.com/model-publishers/octen) Octen-Embedding-8B is a text embedding model developed by Octen for semantic search and retrieval tasks. This model is fine-tuned from Qwen/Qwen3-Embedding-8B and supports multiple languages, providing high-quality embeddings for various applications. - Octen-Embedding-8B ranks #1 on the RTEB Leaderboard with Mean (Task) score of 0.8045 - Excellent performance on both Public (0.7953) and Private (0.8157) datasets - Demonstrates true generalization capability without overfitting to public benchmarks - Supports up to 32,768 tokens context length - Suitable for processing long documents in legal, healthcare, and other domains - High-dimensional embedding space for rich semantic representation… Open weights apache-2.0 7.6B parameters 40,960 tokens sentence-transformers [View model](https://savrn.com/models/octen-embedding-8b) Model · Sentence similarity ### [AX-Qwen3-Embedding-8B-CUDA-AXQ-NVFP4-W4A4](https://savrn.com/models/ax-qwen3-embedding-8b-cuda-axq-nvfp4-w4a4) [AutomatosX](https://savrn.com/model-publishers/automatosx) AXQuant CUDA NVFP4 W4A4 mixed precision development preview. Converted from the original upstream BF16 source, without AWQ. Native E2M1 FP4 weights and inputs use per-16 E4M3FN scales and FP32 global scales. This is a retrieval embedding checkpoint, with no MTP or generative claim. All attention projections and the first/last two MLP blocks retain original BF16. Remaining MLP matrices use NVFP4 W4A4. Saved query instruction, last-token pooling, exactly one (151643), and L2 normalization. The chat (151645) is not appended. Factory conversion uses AXQuant's NumPy reference RTN encoder, independently checked against preserved BF16 source tensors. Source and pooling assets, calibration and… Open weights apache-2.0 7.6B parameters 40,960 tokens vllm [View model](https://savrn.com/models/ax-qwen3-embedding-8b-cuda-axq-nvfp4-w4a4) Model · Sentence similarity ### [AX-Nemotron-3-Embed-8B-CUDA-AXQ-NVFP4-W4A4](https://savrn.com/models/ax-nemotron-3-embed-8b-cuda-axq-nvfp4-w4a4) [AutomatosX](https://savrn.com/model-publishers/automatosx) AXQuant CUDA NVFP4 W4A4 mixed precision development preview. Converted from the original upstream BF16 source, without AWQ. Native E2M1 FP4 weights and inputs use per-16 E4M3FN scales and FP32 global scales. This is a retrieval embedding checkpoint, with no MTP or generative claim. Eligible attention and MLP matrices use NVFP4 W4A4. Embeddings and norms retain original BF16. Saved query: / passage: prefixes, bidirectional attention, mean pooling and L2 normalization. The native vLLM Ministral alias retains iscausal=false and every actual attention layer is verified as encoder-only. Factory conversion uses AXQuant's NumPy reference RTN encoder, independently checked against preserved BF16… Open weights other 8B parameters 262,144 tokens vllm [View model](https://savrn.com/models/ax-nemotron-3-embed-8b-cuda-axq-nvfp4-w4a4) Model · Sentence similarity ### [Qwen3-VL-Embedding-8B](https://savrn.com/models/qwen3-vl-embedding-8b) [Qwen](https://savrn.com/model-publishers/qwen) The Qwen3-VL-Embedding and Qwen3-VL-Reranker model series are the latest additions to the Qwen family, built upon the recently open-sourced and powerful Qwen3-VL foundation model. Specifically designed for multimodal information retrieval and cross-modal understanding, this suite accepts diverse inputs including text, images, screenshots, and videos, as well as inputs containing a mixture of these modalities. While the Embedding model generates high-dimensional vectors for broad applications like retrieval and clustering, the Reranker model is engineered to refine these results, establishing a comprehensive pipeline for state-of-the-art multimodal search. Qwen3-VL-Embedding-8B has the… Open weights apache-2.0 8.1B parameters 262,144 tokens sentence-transformers [View model](https://savrn.com/models/qwen3-vl-embedding-8b) Model · Sentence similarity ### [AX-Qwen3-Embedding-4B-CUDA-AXQ-NVFP4-W4A4](https://savrn.com/models/ax-qwen3-embedding-4b-cuda-axq-nvfp4-w4a4) [AutomatosX](https://savrn.com/model-publishers/automatosx) AXQuant CUDA NVFP4 W4A4 mixed precision development preview. Converted from the original upstream BF16 source, without AWQ. Native E2M1 FP4 weights and inputs use per-16 E4M3FN scales and FP32 global scales. This is a retrieval embedding checkpoint, with no MTP or generative claim. All attention projections and the first/last two MLP blocks retain original BF16. Remaining MLP matrices use NVFP4 W4A4. Saved query instruction, last-token pooling, exactly one (151643), and L2 normalization. The chat (151645) is not appended. Factory conversion uses AXQuant's NumPy reference RTN encoder, independently checked against preserved BF16 source tensors. Source and pooling assets, calibration and… Open weights apache-2.0 4B parameters 40,960 tokens vllm [View model](https://savrn.com/models/ax-qwen3-embedding-4b-cuda-axq-nvfp4-w4a4) Model · Sentence similarity ### [Qwen3-VL-Embedding-2B](https://savrn.com/models/qwen3-vl-embedding-2b) [Qwen](https://savrn.com/model-publishers/qwen) The Qwen3-VL-Embedding and Qwen3-VL-Reranker model series are the latest additions to the Qwen family, built upon the recently open-sourced and powerful Qwen3-VL foundation model. Specifically designed for multimodal information retrieval and cross-modal understanding, this suite accepts diverse inputs including text, images, screenshots, and videos, as well as inputs containing a mixture of these modalities. While the Embedding model generates high-dimensional vectors for broad applications like retrieval and clustering, the Reranker model is engineered to refine these results, establishing a comprehensive pipeline for state-of-the-art multimodal search. Qwen3-VL-Embedding-2B has the… Open weights apache-2.0 2.1B parameters 262,144 tokens sentence-transformers [View model](https://savrn.com/models/qwen3-vl-embedding-2b) ## University of Washington Math AI Lab [All models and datasets](https://savrn.com/model-publishers/uw-math-ai) ## Versions - [ffe9c2a4a1b7](https://savrn.com/models/mathleap-qwen-8b/versions/ffe9c2a4a1b7) · current 2026-10-01 ## Explore More - [All sentence similarity models](https://savrn.com/models/tasks/sentence-similarity) - [All models under apache-2.0](https://savrn.com/models/licenses/apache-2-0) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-10-01. - [Hugging Face record](https://huggingface.co/uw-math-ai/MathLeap-Qwen-8B) - [How the hub is built](https://savrn.com/model-hub/methodology)