GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
Nimbus-Labs
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Nimbus-Labs
Model Tree
Base
Qwen/Qwen3.5-4B-Base
Fine-tuned
this model
Input Modalities
Text
Image
Video
Output Modalities
Text
Supported Functionality
Dedicated Endpoints
| Model | Best fit | Transformers | GGUF | MLX |
|---|---|---|---|---|
| Nimbus-2B | Fast drafting and focused edits | Nimbus-Labs/Nimbus-2B | Nimbus-Labs/Nimbus-2B-GGUF | Nimbus-Labs/Nimbus-2B-MLX-5bit |
| Nimbus-4B | Balanced implementation and debugging | Nimbus-Labs/Nimbus-4B | Nimbus-Labs/Nimbus-4B-GGUF | Nimbus-Labs/Nimbus-4B-MLX-5bit |
| Nimbus-9B v2.1 | Deeper coding and reasoning | Nimbus-Labs/Nimbus-9B-v2.1 | Nimbus-Labs/Nimbus-9B-v2.1-GGUF | Nimbus-Labs/Nimbus-9B-v2.1-MLX-5bit |
The adjacent assets/nimbus-family-footprint.json contains the plotted values. Download size is not runtime memory: context cache and runtime buffers require additional capacity.
| Format | Shards | Weight bytes | Integrity |
|---|---|---|---|
| BF16 safetensors | 5 | 9,078,619,688 (9.08 GB) | SHA256SUMS |
Text-only local files: Nimbus-Labs/Nimbus-4B-GGUF
The released Q5_K_M artifact was evaluated in direct mode on the full HumanEval and MBPP suites with llama.cpp b10007, one answer per task, temperature 0.6, top-p 0.95, top-k 20, and seed 42.
| Benchmark | Passed | Total | pass@1 |
|---|---|---|---|
| HumanEval | 121 | 164 | 73.8% |
| HumanEval+ | 112 | 164 | 68.3% |
| MBPP | 285 | 378 | 75.4% |
| MBPP+ | 232 | 378 | 61.4% |
The adjacent assets/nimbus-4b-evalplus.json is the machine-readable source for this chart.
Use a recent Transformers release compatible with Qwen3.5. Load the repository with trust_remote_code=False, preserve the supplied processor/tokenizer files, and enable thinking through the supplied chat template where supported. Validate generated code before execution.
python
from transformers import AutoProcessor, AutoModelForImageTextToTextmodel_id = "Nimbus-Labs/Nimbus-4B"processor = AutoProcessor.from_pretrained(model_id)model = AutoModelForImageTextToText.from_pretrained(model_id, torch_dtype="auto", device_map="auto")
Qwen/Qwen3.5-4B-Base1001bb4d826a52d1f399e183466143f4da7b741bSHA256SUMSrelease-manifest.jsonNimbus prominently credits Qwen3.5 as the foundation for this model family. Nimbus-9B-v2.1 additionally credits DeepReinforce's Ornith-1.0-9B as its immediate upstream.
Local coding assistance, code explanation, debugging, test generation, and bounded tool-aware workflows. Host applications must enforce permissions, sandboxing, timeouts, and verification.
The model can produce incorrect, insecure, incomplete, or non-compiling code. Benchmark performance does not guarantee project-level correctness. GGUF artifacts are text-only even though this Transformers checkpoint includes multimodal components.
See LICENSES.md, THIRD_PARTY_NOTICES.md, and the bundled Apache-2.0 text. The model is a derivative distribution; Nimbus attribution does not replace upstream attribution.