# DualMind-TKD-Agentic-1.7B by Convergent Intelligence Source: https://savrn.com/models/dualmind-tkd-agentic-1-7b Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve DualMind-TKD-Agentic-1.7B (1.7B 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 | 3.4 GB | 4.1 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 | | 8-bit | 1.7 GB | 2.1 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 | 0.9 GB | 1.0 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 24, 2026. [DualMind-TKD-Agentic-1.7B on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/dualmind-tkd-agentic-1-7b/gpus) ## Model Card DualMind TKD Agentic 1.7B is a two-stage derivative of Qwen/Qwen3-1.7B. It combines topology-guided mathematical knowledge distillation with assistant-masked agentic and function-calling specialization. teacher distillation topology, gap-energy diagnostics, and phase-weighted Explore/Examine/Response supervision Stage 1 was designed to transfer mathematical reasoning behavior while placing additional learning pressure on derivation, verification, and high-discrepancy reasoning transitions. - Tool schemas, user messages, and tool-result messages were visible as context but excluded from direct loss - Mathematical replay was mixed into Stage 2 to reduce catastrophic forgetting The files in… Excerpt from the card by Convergent Intelligence, licensed other. ## Configuration Architecture Qwen3ForCausalLM Context length (tokens) 40,960 Layers 28 Hidden size 2,048 Feed-forward size 6,144 Attention heads 16 Key/value heads 8 Head dimension 128 Vocabulary size 151,936 Model type qwen3 ## Identity and Version Repository reaperdoesntknow/DualMind-TKD-Agentic-1.7B Publisher Convergent Intelligence Task Text generation Modality Text Library transformers Parameters 1.7B parameters Languages en Revision d22b1bc05cc09e9e3278fcdd9136dd996202628d First published 2026-07-12 Last updated 2026-09-18 ## Files and Weights 15 files, 6.9 GB in total. The weights are 1 file totalling 6.9 GB in safetensors. Weights1 file · 6.9 GB Configuration7 files · 42.7 KB Tokenizer2 files · 11.4 MB Documentation1 file · 4.0 KB Other3 files · 74.4 KB Repository1 file · 1.6 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model.safetensors | Weights | 6.9 GB | c3f6b13ea36d | | config.json | Configuration | 1.4 KB | — | | generation_config.json | Configuration | 188 B | — | | release_manifest.json | Configuration | 983 B | — | | training_artifacts/DualMind100_agentic_trainer_state.json | Configuration | 24.1 KB | — | | training_artifacts/DualMind100_config.json | Configuration | 2.7 KB | — | | training_artifacts/config.json | Configuration | 2.7 KB | — | | training_artifacts/trainer_state.json | Configuration | 10.6 KB | — | | README.md | Documentation | 4.0 KB | — | | chat_template.jinja | Other | 4.2 KB | — | | training_artifacts/DualMind100_train_log.jsonl | Other | 35.1 KB | — | | training_artifacts/train_log.jsonl | Other | 35.1 KB | — | | .gitattributes | Repository | 1.6 KB | — | | tokenizer.json | Tokenizer | 11.4 MB | be75606093db | | tokenizer_config.json | Tokenizer | 693 B | — | ## License and Download License other Access Open weights, no gate Download size 6.9 GB [Download from Convergent Intelligence](https://huggingface.co/reaperdoesntknow/DualMind-TKD-Agentic-1.7B) Released by Convergent Intelligence through its official repository on Hugging Face. ## Built From - Derived from [Qwen/Qwen3-1.7B](https://savrn.com/models/qwen3-1-7b) - Trained on (disclosed) 0xZee/dataset-CoT-Advanced-Calculus-268 - Trained on (disclosed) NousResearch/hermes-function-calling-v1 ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 6.9 GB | | 16-bit | 3.4 GB | | 8-bit | 1.7 GB | | 4-bit | 0.9 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Questions About DualMind-TKD-Agentic-1.7B ### How much GPU memory does DualMind-TKD-Agentic-1.7B need? About 4.1 GB at 16-bit and 1 GB at 4-bit: the weights (1.7B parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run DualMind-TKD-Agentic-1.7B 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. ### What license is DualMind-TKD-Agentic-1.7B released under? other, as its publisher declares it. Read the license text before commercial use. ### What is DualMind-TKD-Agentic-1.7B's context length? 40,960 tokens, from the maximum position embeddings in its published configuration. ## Similar Models Model · Text generation ### [Qwen3-1.7B-Base](https://savrn.com/models/qwen3-1-7b-base) [Qwen](https://savrn.com/model-publishers/qwen) Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Building upon extensive advancements in training data, model architecture, and optimization techniques, Qwen3 delivers the following key improvements over the previously released Qwen2.5: Qwen3-1.7B-Base has the following features: For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our blog, GitHub, and Documentation. The code of Qwen3 has been in the latest Hugging Face transformers and we advise you to use the latest version of transformers. With transformers<4.51.0, you will… Open weights apache-2.0 1.7B parameters 32,768 tokens transformers [View model](https://savrn.com/models/qwen3-1-7b-base) Model · Text generation ### [dQwen3-1.7B-Base](https://savrn.com/models/dqwen3-1-7b-base) [IFML](https://savrn.com/model-publishers/ut-ifml) A masked diffusion language model adapted from Qwen3-1.7B. The backbone is full attention, and every layer is made bidirectional. It is the control model in the paper's matched comparison against the hybrid dQwen3.5-2B. This is a base model, with no instruction tuning. Paper: dQwen3.5: Hybrid-Attention Diffusion Language Models. Code: https://github.com/AntonXue/dQwen Needs a CUDA GPU and transformers>=5.13 (tested with torch 2.7.1+cu128, flash-linear-attention 0.5.1). generate decodes the whole canvas at once, committing positions above a confidence threshold (tau=0.9); pass blocklength=32 for left-to-right block decoding, or tau=None, stepsperblock=k for a fixed budget. The 50B-token… Open weights apache-2.0 1.7B parameters 40,960 tokens transformers [View model](https://savrn.com/models/dqwen3-1-7b-base) Model · Text generation ### [qwen3-1.7b-grpo](https://savrn.com/models/qwen3-1-7b-grpo) [Op](https://savrn.com/model-publishers/op12138) This model is a fine-tuned version of None. It has been trained using TRL. This model was trained with GRPO, a method introduced in DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models. Open weights 1.7B parameters 40,960 tokens transformers [View model](https://savrn.com/models/qwen3-1-7b-grpo) Model · Text generation ### [Qwen3-1.7B-teacher-note-severity-v2](https://savrn.com/models/qwen3-1-7b-teacher-note-severity-v2) [Jeremie Rostan](https://savrn.com/model-publishers/jeremierostan) Continued LoRA fine-tune of Qwen3-1.7B-teacher-note-severity (itself a LoRA of Qwen/Qwen3-1.7B, 32K context). v2 adds a location field. Given a teacher note (or a running log), it outputs: {"category": "commendation|misbehavior|academicconcern", "location": "inclass|outsideclass", "severity":, "escalate": } Commendations are negative; routine notes 5-55; severity >= 60 escalates to admin. Trained on synthetic data: jeremierostan/teacher-notes-severity-v2 (continues v1 training, LR 1e-4, 2 epochs). Open weights apache-2.0 1.7B parameters 40,960 tokens transformers [View model](https://savrn.com/models/qwen3-1-7b-teacher-note-severity-v2) Model · Text generation ### [commercecore-qwen3-1.7b](https://savrn.com/models/commercecore-qwen3-1-7b) [Arghya Mukherjee](https://savrn.com/model-publishers/arghya2030) A small (1.7B parameter), self-hostable model that parses natural-language shopping queries into structured constraints — trained for under $10 in total compute + API cost. Beats every tested frontier model on the primary held-out benchmarks; an honest, independent fresh-query test below shows this advantage does not hold universally — read that section before relying on any headline number. Model weights + model card: https://huggingface.co/arghya2030/commercecore-qwen3-1.7b Source code + docs: https://github.com/arghya05/commercecore Status: research / proof-of-concept. Read "What this is NOT" before using in production. Ecommerce search boxes get queries like "black waterproof trainers… Open weights apache-2.0 1.7B parameters 40,960 tokens [View model](https://savrn.com/models/commercecore-qwen3-1-7b) Model · Text generation ### [qwen3-1.7b-chat](https://savrn.com/models/qwen3-1-7b-chat) [Noeme](https://savrn.com/model-publishers/noeme) This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). Open weights 1.7B parameters 32,768 tokens transformers [View model](https://savrn.com/models/qwen3-1-7b-chat) ## Convergent Intelligence [All models and datasets](https://savrn.com/model-publishers/reaperdoesntknow) ## Versions - [d22b1bc05cc0](https://savrn.com/models/dualmind-tkd-agentic-1-7b/versions/d22b1bc05cc0) · current 2026-09-18 ## Explore More - [All text generation models](https://savrn.com/models/tasks/text-generation) - [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 2026-10-21. - [Hugging Face record](https://huggingface.co/reaperdoesntknow/DualMind-TKD-Agentic-1.7B) - [How the hub is built](https://savrn.com/model-hub/methodology)