Nimbus-4B-MLX-4bit

Nimbus-4B GGUF

Text-only llama.cpp artifacts for Nimbus-4B. Q5_K_M is the quality-first local default; Q4_K_M is listed only where it actually exists.

Choose a Nimbus model

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.

Downloads

llama.cpp

Validated release runtime: llama.cpp b10007. Native thinking uses the supplied Qwen/Ornith chat template and DeepSeek-style reasoning parsing.

llama-server --model Nimbus-4B-Q5_K_M.gguf --ctx-size 65536 --n-gpu-layers all --reasoning-format deepseek

Evaluation

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.

The adjacent assets/nimbus-4b-evalplus.json is the machine-readable source for this chart.

Provenance and scope

• Quantized from Nimbus-Labs/Nimbus-4B
• Foundation: Qwen3.5
• GGUF files are text-only; the Transformers repository retains the multimodal components.
• Do not infer memory fit from file size alone; context KV cache and runtime buffers require additional memory.

Licenses and notices

See LICENSES.md, THIRD_PARTY_NOTICES.md, and LICENSES/Apache-2.0.txt.

Project

Nimbus8 · Transformers checkpoint