# Kimi-K3-DSpark vs Qwen3-1.7B-Base: Specs, License and GPU Cost Source: https://savrn.com/models/compare/kimi-k3-dspark-vs-qwen3-1-7b-base Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- | Field | [Kimi-K3-DSpark](https://savrn.com/models/kimi-k3-dspark) RadixArk/Kimi-K3-DSpark | [Qwen3-1.7B-Base](https://savrn.com/models/qwen3-1-7b-base) Qwen/Qwen3-1.7B-Base | | --- | --- | --- | | Publisher | RadixArk | Qwen | | Task | Text generation | Text generation | | Modality | Text | Text | | Parameters, as reported | 2.2B parameters | 1.7B parameters | | Architecture | DSparkDraftModel | Qwen3ForCausalLM | | Library | transformers | transformers | | Context length | 1,048,576 tokens | 32,768 tokens | | Repository size | 4.5 GB | 3.5 GB | | Artifact formats | safetensors | safetensors | | License | Not stated | apache-2.0 | | Access | Open weights, no gate | Open weights, no gate | | Memory at 16-bit (weights and margin) | 5.4 GB | 4.1 GB | | Cheapest GPUs at 16-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 | | Memory at 4-bit (weights and margin) | 1.3 GB | 1 GB | | Cheapest GPUs at 4-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 | | Revision viewed | 3c5bac301d9c | ea980cb0a6c2 | | Downloads reported by the hub | 3.9M | 1.1M | | Last observed | 2026-10-23 | 2026-09-29 | An evaluation row appears only where at least two of these models report the same benchmark with the same stated configuration, metric, unit and setup. Different evaluators stay named in each cell. Values are shown as reported: no unit conversion, no ranking. ## SAVRN's Notes on Kimi-K3-DSpark Read this as a companion, not a model you serve on its own. RadixArk trained Kimi-K3-DSpark as a DSpark speculator for the Kimi K3 target, a 2.2 billion parameter draft built for faster inference through speculative decoding. Five layers and 4.5 GB of weights keep it light: 5.4 GB of memory at 16-bit, 2.7 GB at 8-bit, 1.3 GB at 4-bit, and one MI300X with 192 GB at $1.85 an hour on-demand is the cheapest listing we track. That covers the draft only; the Kimi K3 target sizes your box. The license field is empty, so get written terms from RadixArk before deployment; open access is not permission to run it commercially. Match your stack too: the checkpoint was trained with SpecForge on hidden states from a live SGLang target engine, and the 1,048,576 token context is the draft's ceiling, so the target needs the same window. SAVRN Research, 2026-09-18 ## SAVRN's Notes on Qwen3-1.7B-Base A 1.7B-parameter base model — no instruction tuning — with a 32,768-token context. Working memory is 4.1 GB at 16-bit, 2.1 GB at 8-bit and 1.0 GB at 4-bit, so the cheapest listed setup, one MI300X at $1.85 an hour, is the same card the Index quotes for a 122B quant. The real point: at this size you serve it on one small GPU, an old 8 GB card, or even CPU, not a 192 GB accelerator. Apache 2.0 permits commercial use with the standard notice and patent terms. Pick the base over the instruct Qwen3-1.7B only if you are doing your own fine-tuning or evaluation; for anything user-facing the instruct variant saves you a step. Weights publish in bfloat16. It draws 1.1M downloads a month, and the Index shows a long tail of community finetunes built on exactly this checkpoint. SAVRN Research ## Questions ### Which is larger, Kimi-K3-DSpark or Qwen3-1.7B-Base? Kimi-K3-DSpark (2.2B parameters) is larger than Qwen3-1.7B-Base (1.7B parameters), by the parameter counts their publishers report. ### Which is cheaper to run, Kimi-K3-DSpark or Qwen3-1.7B-Base? At 4-bit, Kimi-K3-DSpark fits on 1x MI300X from $1.85 an hour and Qwen3-1.7B-Base on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists. ### Can I use Qwen3-1.7B-Base commercially? Yes. Qwen3-1.7B-Base 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. ## Related Comparisons - [Kimi-K3-DSpark vs Llama-3.2-3B-Instruct](https://savrn.com/models/compare/kimi-k3-dspark-vs-llama-3-2-3b-instruct) - [Kimi-K3-DSpark vs Qwen3-1.7B](https://savrn.com/models/compare/kimi-k3-dspark-vs-qwen3-1-7b) - [Qwen2.5-1.5B-Instruct vs Qwen3-1.7B-Base](https://savrn.com/models/compare/qwen2-5-1-5b-instruct-vs-qwen3-1-7b-base)