Ornith-1.5-35B-A3B is a self-improving agentic coding model from the Ornith Team. It extends Ornith-1.0 by expanding the self-improvement loop from scaffold and rollout optimization to jointly optimizing task generation, scaffold construction, and solution rollouts — continuously generating new training tasks, discovering effective strategies, and improving the policy through reinforcement learning.

Activating only ~3B parameters per token, it significantly outperforms its similar-sized peer Qwen3.6-35B across all coding and agentic benchmarks: Terminal-Bench 2.1 67.8, SWE-bench Verified 79, SWE-bench Pro 59.6, SWE-bench Multilingual 71.4, NL2Repo 46.2, MCP-Atlas 70.2, ClawEval 72.5.

This GGUF package includes the mmproj-BF16.gguf vision projector for multimodal (image + text) capabilities with llama.cpp. Unlike Ornith-1.0, the MTP layer is native to the model — no external grafting required. License: MIT.

llama.cpp (text only)

hf download SC117/Ornith-1.5-35B-A3B-MTP-APEX-GGUF --include "*.gguf" --local-dir ./models ./llama-server -m ./models/Ornith-1.5-35B-A3B-MTP-APEX-I-Compact.gguf -ngl 99 -c 131072

llama.cpp (vision + text)

./llama-server -m ./models/Ornith-1.5-35B-A3B-MTP-APEX-I-Compact.gguf --mmproj ./models/mmproj-BF16.gguf -ngl 99 -c 131072

These GGUF files are quantized using APEX, an MoE-aware mixed-precision quantization technique. APEX classifies every tensor by its role — routed expert, shared expert, or attention — and applies a layer-wise precision gradient, giving sensitive edge layers higher precision and compressing redundant middle layers more aggressively.

APEX beats Q8_0 perplexity at half the size — and even beats F16.

Short answer: the tiers are bit-allocation strategies, not a size ladder. APEX assigns precision per tensor from measured importance, so file size does not grow monotonically with the tier name.

I-Quality keeps every sensitive tensor high-precision — attention at Q6_K in all 40 blocks, shared experts at Q8_0, edge blocks high as well — but compresses the redundant middle routed experts (blk.10–29) aggressively to IQ4_XS. Routed experts carry most of an MoE's parameters, and the importance analysis shows the middle blocks absorb this compression with virtually no measurable loss. That is where the bytes are saved.

I-Balanced is the conservative, uniform profile: no tensor anywhere below Q5_K. Uniformity simply costs more bytes.

So bigger does not mean better. I-Quality is the smarter bit allocation and remains the highest-quality preset despite being ~2.3 GB smaller; if you need a smaller file, step down to I-Compact or I-Mini instead of picking by file size.

The two tiers are identical everywhere except the middle routed-expert band — that single band is the whole size difference.