DeepReinforce
DeepReinforce
CodeOpen Weights (MIT) Verified Architecture & SpecsFree ($0 API Tokens)

Ornith 1.5 35B A3B

Mixture-of-experts coding-reasoning model for agentic software tasks, tool use, and image understanding

Technical Architecture & Execution Specifications
Architecture Overview

Ornith 1.5 35B A3B

Mixture-of-experts coding-reasoning model for agentic software tasks, tool use, and image understanding

Memory Math Breakdown
  • • FP16 Weights = 35.0B × 2B = 70.00 GB
  • • INT4 Weights = 35.0B × 0.55B = 19.25 GB
  • • KV Cache (262144 ctx, FP16) ≈ 50.00 GB
  • • Activation Buffer = ~20% overhead
Supported Modalities
textimage

Hardware & Execution ParametersCode

Total Parameter Count35B
Active Parameters (MoE)Dense Architecture
Context Window Capacity262,144 tokens
Model Weights Footprint70.0 GB (FP16) / 19.3 GB (INT4)
Distribution LicenseOpen Weights (MIT)
Standard API Pricing (1M Tokens)Free / Self-Hosted
Model Heritage & Evolutionary Lineage

Genealogical Graph & Evolutionary Provenance

Tracing foundational base architecture ancestry, architectural successors, scale siblings, and reasoning distillation derivatives.

Independent Foundation Checkpoint

Ornith 1.5 35B A3B operates as an autonomous foundation model architecture without direct precursor derivatives in this catalog.

Root Architecture Node
AI Model Architecture & Intelligence

Architecture Engineering & Capability Deep-Dive

An objective architectural evaluation of Ornith 1.5 35B A3B by DeepReinforce, analyzing underlying compute dynamics, memory constraints, and deployment economics.

Topology & Attention Mechanics

A robust autoregressive transformer utilizing standard attention patterns for predictable and coherent token generation.

Architecture Type:Advanced Transformer

Evaluation Profile & Reasoning

Exhibits frontier-tier behavior in reasoning and coding.

Domain Specialty:Code

LLM Hardware Sizing & Serving

For open deployments via vLLM/SGLang, quantization (INT4/AWQ) is heavily recommended to fit dense memory constraints, or multi-GPU pipeline parallelism for full FP16.

KV Cache Mgmt: PagedAttention / FlashAttention-3
Hosting Type:Open Weights (MIT)

Inference Economics & Workflows

Well-suited for enterprise pipelines where capability is balanced against per-million token costs.

Enterprise Fit:Production Ready
Production Trade-Offs & Capability Balance

Architectural Strengths vs. Considerations

An objective balance sheet analyzing the operational advantages and production constraints of deploying Ornith 1.5 35B A3B.

Key Architectural Strengths

  • Massive 262,144-token context allows full-repository and book-length ingestion.

Operational Considerations

  • 128k+ token prefill stages become heavily compute-bound and balloon KV cache without PagedAttention chunking.
LLM Hardware Sizing & Runtime Compatibility

Inference Runtimes & Hardware Sizing

Deployment targets, inference engines, and memory requirements for Ornith 1.5 35B A3B.

Recommended Hardware Profile:
1x RTX 3090 / 4090 (24GB) or Mac M-Series (32GB+)
High-End Consumer GPU (24 GB VRAM)
Est. 84.0 GB (FP16) / 23.1 GB (INT4)
Production Serving Recipes
vLLM Production
python3 -m vllm.entrypoints.openai.api_server --model Ornith 1.5 35B A3B --tensor-parallel-size 1 --gpu-memory-utilization 0.95 --max-model-len 4096 --enable-chunked-prefill
Ollama / llama.cpp
ollama run ornith 1.5 35b a3b
SGLang Structured
python3 -m sglang.launch_server --model-path Ornith 1.5 35B A3B --tp 1 --trust-remote-code
TGI Serving
text-generation-launcher --model-id Ornith 1.5 35B A3B --num-shard 1 --max-batch-prefill-tokens 32000
Supported Inference Engines
vLLM

High-throughput PagedAttention server

Supported
Ollama

One-click CLI & local desktop serving

Supported
SGLang

Fast multi-turn structured decoding

Supported
TGI

Text Generation Inference

Supported
Llama.cpp

GGUF CPU/Apple Silicon execution

Supported
Precision & Quantization Formats
BF16 / FP16Full Precision

~84.0 GB VRAM required

FP8 (E4M3)Native FP8

~42.0 GB VRAM (Hopper speedup)

AWQ / GPTQ (4-bit)Activation-Aware

~23.1 GB VRAM

GGUF (Q4_K_M)Quantized Binary

CPU RAM / Apple Silicon optimized

Commercial Rates & Inference Costs

API & Deployment Pricing

Open-weights model available for local and private cloud deployment. Compute costs depend on the target GPU hardware instance.

Deployment TierPricing Structure
Open Checkpoint Weights$0.00 (Free Download)
Inference Token Consumption$0.00 / Token
Inference Cost & ROI Engine
Market Cloud Rate
Prompt / Input Volume:50M Tokens / mo
1M500M1,000M
Generated / Output Volume:10M Tokens / mo
1M250M500M
Estimated Monthly Spend
$64.00/ mo
Input (50M @ $0.80/1M):$40.00
Output (10M @ $2.40/1M):$24.00
Cloud GPU Breakeven Ratio
RunPod RTX 4090 ($316/mo)0.20x spend
Lambda 1x H100 ($1,800/mo)0.04x spend
💡 Open-weights model. You can self-host for $0 token API charge or consume via managed serverless endpoints at the rates shown above.
Similar Frontier Models & Alternatives
Explore All Comparisons

Comparable Foundation Architectures

Alternative models in the Code class with similar capabilities, context windows, or deployment profiles.

DeepSeekCode

DeepSeek V4 Flash Vision Exp

Context:1000k ctx
Parameters:Proprietary
Input Rate:$0.44/1M
Zhipu AICode

GLM-5.3

Context:1000k ctx
Parameters:Proprietary
Input Rate:Free / Self-Host
Alibaba CloudCode

Qwen3.8 2.4T A95B

Context:262k ctx
Parameters:95B
Input Rate:Free / Self-Host
Integration & Deployment
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("DEEPREINFORCE_KEY", "EMPTY"),
    base_url="http://localhost:8000/v1"
)

response = client.chat.completions.create(
    model="deepreinforce-ornith-1.5-35b-a3b",
    messages=[{"role": "user", "content": "Explain quantum superposition in 2 sentences."}]
)
print(response.choices[0].message.content)
Frequently Asked Questions

Frequently Asked Questions about Ornith 1.5 35B A3B

Essential facts, architectural specs, hardware constraints, and pricing answers for Ornith 1.5 35B A3B.

To run Ornith 1.5 35B A3B (35B) locally, you generally need Depends on quantization. We recommend using quantized GGUF/AWQ formats with Ollama or vLLM to optimize memory footprint.

Primary Sources & Access Repositories

All technical specifications, parameter distributions, context architectures, and benchmark evaluations for Ornith 1.5 35B A3B are audited against primary source release documentation, research whitepapers, and verified vendor API endpoints.

api id:deepreinforce/ornith-1.5-35b-a3b