GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
rwillox
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
rwillox
Model Tree
deepreinforce-ai/Ornith-1.0-35B
Input Modalities
Output Modalities
Supported Functionality
Ornith-1.0-35B by DeepReinforce AI — a 33.4B parameter MoE model with vision capabilities, built on the Qwen3.5 architecture.
| Detail | Value |
|---|---|
| Tool | spark-auto-round v0.14.3 by whpthomas |
| Format | W4A16 (INT4 weights, group_size=128, symmetric) |
| Dataset | opencode-instruct (128 samples, seqlen=2048) |
| Iterations | 200 per block |
| Batch size | 2 |
| Hardware | DGX Spark (GB10, 128 GB unified) |
| Peak RAM | 115.71 GB |
| Peak VRAM | 22.65 GB |
| Metric | Value |
|---|---|
| Avg cosine similarity | 0.9188 |
| Avg PSNR | 50.8 dB |
| Blocks | 39 transformer layers quantized |
| Format | Size |
|---|---|
| Original (BF16) | ~62.2 GB |
| Quantized (INT4) | ~20 GB (5 safetensor shards) |
Compatible with vLLM (auto-detects quantization: auto-round, uses Marlin kernel):
bash
vllm serve yourname/Ornith-1.0-35B-int4-AutoRound \--trust-remote-code \--enable-auto-tool-choice \--tool-call-parser qwen3_xml \--reasoning-parser qwen3 \--load-format safetensors