Search public pages, research tools, and SAVRN solutions.
spark-darwin-17b-3way is an open-weight model for text generation from Charlie, released under Apache License 2.0. It has 1.7B parameters and a 1,048,576-token context. At 16-bit it needs about 4.1 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
Darwin uniform-soup of 3 Spark2.5-1.7B donors (226/226 tensors verified). Agentic/tool-use + uncensored + multilingual blend. Distillation donor for the 4B program. Needs transformers==5.17.0 + trustremotecode=True.
What it takes to serve spark-darwin-17b-3way (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 (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 1.7 GB | 2.0 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.9 GB | 1.0 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x 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, read Oct 15, 2026.
spark-darwin-17b-3way on every accelerator the SAVRN Index prices, at every precision
By Charlie, published under apache-2.0, revision 26a26a42e6a6.
Darwin uniform-soup of 3 Spark2.5-1.7B donors (226/226 tensors verified). Agentic/tool-use + uncensored + multilingual blend. Distillation donor for the 4B program. Needs transformers==5.17.0 + trustremotecode=True.
Darwin uniform-soup of 3 Spark2.5-1.7B donors (226/226 tensors verified).
Agentic/tool-use + uncensored + multilingual blend. Distillation donor for
the 4B program. Needs transformers==5.17.0 + trust_remote_code=True.
12 files, 3.4 GB in total. The weights are 1 file totalling 3.4 GB in safetensors.
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 3.4 GB | d8ac17aa686c |
| config.json | Configuration | 1.9 KB | — |
| configuration_spark.py | Configuration | 5.0 KB | — |
| darwin_report.json | Configuration | 436 B | — |
| generation_config.json | Configuration | 296 B | — |
| modeling_spark.py | Configuration | 19.4 KB | — |
| README.md | Documentation | 476 B | — |
| chat_template.jinja | Other | 4.8 KB | — |
| darwin_W.npy | Other | 1.0 KB | 316584b8c667 |
| .gitattributes | Repository | 1.5 KB | — |
| tokenizer.json | Tokenizer | 10.1 MB | — |
| tokenizer_config.json | Tokenizer | 402 B | — |
Released by Charlie through its official repository on Hugging Face. Read the license.
| Precision | Weights in memory |
|---|---|
| As published | 3.4 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.
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.
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.
Yes. spark-darwin-17b-3way 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.
1,048,576 tokens, from the maximum position embeddings in its published configuration.
LuminoLex-1.7B is Bangladesh’s first decoder-only language model pretrained from scratch. Built on a sparse Mixture-of-Experts (MoE) architecture, it contains 1.7 billion total parameters while activating only ~410 million parameters per token. By combining an always-on shared expert with Grouped-Query Attention (GQA), LuminoLex-1.7B delivers fast, memory-efficient inference without sacrificing model capacity. This model is released under the Apache License 2.0.
The first defense AI reasoning model on Hugging Face. Shepherd-Alpha is a tactical reasoning model fine-tuned on dual-perspective military scenario analysis using BiCell Depth Dispersal — a novel training methodology that partitions transformer layers by abstraction depth and trains them asymmetrically to separate representation encoding from task-specific reasoning. Developed by Convergent Intelligence LLC: Research Division Given a tactical scenario, Shepherd-Alpha produces structured dual-perspective analysis: - Attack reasoning — how an adversary would exploit the situation - Defense reasoning — how to counter, mitigate, and survive The model is trained to think like both attacker and…
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…
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…
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…
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.