GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
curator-research
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
curator-research
Model Tree
Qwen/Qwen3-8B
Input Modalities
Output Modalities
Supported Functionality
Project workflow routing and tool selection.
Assessment: Routing adapter that beats a fixed-action baseline by 9 of 48 turns and matches the teacher on the paired requests. Tests replay one turn without executing tools.
Architecture: Qwen/Qwen3-8B · Artifact: adapter · Mode: thinking-on.
Evaluation pools and paired comparisons are described below. This release is shown in bold.
| HF model | Correct next action | Best fixed action | Paired student | Paired teacher | Valid JSON |
|---|---|---|---|---|---|
| Qwen3-8B-Curator-0.1.0-Orchestration-Thinking-OFF | 30/48 | 22/48 | 8/18 | 11/18 | .875 |
| Qwen3-8B-Curator-0.1.0-Orchestration-Thinking-ON | 31/48 | 22/48 | 11/18 | 11/18 | .854 |
| Qwen3.6-35B-A3B-Curator-0.1.0-Orchestration-Thinking-OFF | 26/48 | 20/48 |
Next action means selecting the reference's first tool, or correctly selecting no tool. Best fixed action is the score of always choosing the pool's most common action; every adapter beats it, by 6 to 9 turns. Across the four paired groups, students score 37/67 and the teacher 40/67. Some requests recur across adapters; these are 67 comparisons, not 67 independent requests. Each full evaluation uses its own 48-turn pool. Tests replay one turn with tool execution disabled.
One NVIDIA A100 80 GB, vLLM 0.29. Each row describes a shared serving package.
| Package / representative HF model | Base weights | Single stream | Concurrent throughput | GPU J/token | KV capacity (tokens) |
|---|---|---|---|---|---|
| Llama-3.3-Qwen3-8B-Curator-0.1.0-Enrichment-Thinking-ON + 6 sibling adapters (AWQ) | 6.1 GB | 111 tok/s | 684 tok/s at 32 | .56 | 471,200 |
| Llama-3.3-Qwen3.6-35B-A3B-Curator-0.1.0-Enrichment-Thinking-ON + 3 sibling adapters (W4A16) | 21.8 GB |
Student sweeps used 2,048 input / 256 output tokens and cold cache. The teacher figure comes from a 180-second warm window with different output lengths. Ratios between these rows combine model and workload effects. Energy covers sampled GPU board power. The 8B base occupies about one-sixth of the teacher's weight storage and serves seven adapters. Nemotron ON throughput remains unmeasured.
Recorded result: selection-time composite 0.791 (mean of the JSON, tool-name, next-action and template checks).
Comparison pool: 48 turns.
From the training record; run dates were not preserved.
Load Qwen/Qwen3-8B with a compatible PEFT runtime and attach this adapter. The measured weight files match the published weight files; the immutable public loading pin is shown below.
Full-precision PEFT loading example, with a pinned public base. The reported 8B serving measurements used the 4-bit AWQ package identified in the tables.
python
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-8B", revision="b968826d9c46dd6066d109eabc6255188de91218")base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-8B", revision="b968826d9c46dd6066d109eabc6255188de91218", torch_dtype="auto", device_map="auto")model = PeftModel.from_pretrained(base, "curator-research/Qwen3-8B-Curator-0.1.0-Orchestration-Thinking-ON", revision="7141032122d01599e41325134f86c7d50917b6da")A single compatible Qwen/Qwen3-8B base can serve this family of 7 adapters. Register each immutable adapter snapshot with --enable-lora --lora-modules alias=./adapter, then select its alias through the HTTP request model field. This reuses the base weights for fast task switching and GPU-memory reuse. Size the LoRA slots, context and concurrency for the deployment. The 8B and 35B families each require their own base.
Set the chat template's enable_thinking option to true for this variant. The base templates think by default, and an adapter alias does not change the template. The 1 October results used Curator's training-time prompt format; this chat-template setting was not separately evaluated.
Curator publishes these weights as an experimental release of its applied model research, with its own measurements on held-out data. Training data and prompts remain private, so the published scores cannot be reproduced outside Curator; evaluate this exact revision on your own data before production use.
Released under Apache-2.0, the base's licence (LICENSE, NOTICE.txt). Training examples describe project execution logs, routing decisions and tool schemas.
Read the model overview and evaluation boundaries, explore the Curator Research organisation, and follow Curator Research on LinkedIn.
| 11/19 |
| 10/19 |
| 1.000 |
| Qwen3.6-35B-A3B-Curator-0.1.0-Orchestration-Thinking-ON | 32/48 | 23/48 | 7/12 | 8/12 | 1.000 |
| 94 tok/s |
| 1,088 tok/s at 32 |
| .30 |
| 1,929,911 |
| Llama-3.3-Nemotron-Cascade-2-30B-A3B-Curator-0.1.0-Enrichment-Thinking-OFF (BF16) | 63.2 GB | 154 tok/s | 1,166 tok/s at 32 | .33 | 1,358,506 |
| Llama 3.3 70B AWQ | 39.8 GB | — | 107 tok/s at 16, warm | 3.70 | 108,976 |