Nimbus-9B-v2.1-GGUF

Nimbus-9B-v2.1 GGUF

Text-only llama.cpp artifacts for Nimbus-9B-v2.1. 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-9B-v2.1-Q5_K_M.gguf --ctx-size 65536 --n-gpu-layers all --reasoning-format deepseek

Evaluation

The released Q5_K_M artifact was evaluated with llama.cpp b10007 on Vulkan, native thinking, one answer per task, temperature 0.6, top-p 0.95, top-k 20, seed 42, and the official network-disabled EvalPlus scorer. The base run allowed 32,768 completion tokens. Each original length-plus-empty nonresponse received exactly one preserved 60,000-token recovery attempt; there was no repeated resampling.

Three HumanEval and seven MBPP truncations recovered at the larger limit. Two HumanEval and three MBPP nonresponses remained zero-valued. “Plus” uses EvalPlus' official base-and-plus pass condition.

The adjacent assets/nimbus-9b-v2.1-evalplus.json is the machine-readable source for this chart.

Release landscape

This is a capability and packaging comparison, not a cross-model score claim. Other publishers' benchmarks use different harnesses, prompts, inference budgets, and hardware, so they are not mixed into the Nimbus EvalPlus chart.

Nimbus-9B v2.1 inherits its architecture and foundation capabilities from Qwen3.5 through Ornith. Nimbus' contribution is the post-training, release packaging, quantization, and exact evaluation reported above—not authorship of the foundation model.

Provenance and scope

• Quantized from Nimbus-Labs/Nimbus-9B-v2.1
• Foundation: Ornith-1.0-9B on Qwen3.5-9B
• 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