Model overview
Qwen3-4B in 4-bit MLX format for Apple Silicon. This is the first LittleBit release: a small, fast model for running locally on a Mac. > **What this is:** standard MLX 4-bit post-training quantization (group size 64, > about 4.5 bits per weight). It is **not** the sub-1-bit LittleBit-2 method. The > sub-1-bit (0.55 bpw) Qwen3 builds are in progress; the training recipe is in > LittleBitLLM/littlebit. These numbers come from one short generation run. We have not run benchmark evals on this build. Expect quality close to the BF16 Qwen3-4B, as is usual for 4-bit group quantization.
Key features
特点摘要待依据来源补齐，不凭模型名称推断能力。
Limitations & considerations
Sources are insufficient to establish specific limitations. Verify task performance, latency, data policies, licensing and version lifecycle.
Source prices & cost analysis
Prices vary by channel, region and configuration. Channel quotes are listed independently and are not treated as a single official provider price.
| Source / channel | Input | Output | Billing unit | Collected at |
|---|---|---|---|---|
| No verified prices yet. Check the source channel. | ||||
Estimate monthly base token costs
Estimates exclude cache discounts, tiered pricing, multimodal surcharges, web search, taxes and additional reasoning output.
Public benchmarks & run configuration
暂无已采集的可核验公开评分。模型未上榜不代表能力较低。
View full indexed rankings →Frequently asked questions
Do open weights permit free commercial use?
Not necessarily. Check the version license, commercial conditions and usage policies. Self-hosting incurs compute and maintenance costs.
Are these real-time billing prices?
These are timestamped source snapshots, not live billing prices. Check the channel for current versions, regions, discounts and billing methods.
Sources & traceability
许可证：apache-2.0。模型介绍与第三方评测均以原来源的具体版本和方法为准。