# Throughput Benchmark — glm53

- **Run ID**: `2026-09-22T08-01-24.526186Z_55a62203`
- **Date**: `2026-09-22T08:01:24.526501+00:00`
- **Mode**: throughput-only
- **tool-eval-bench**: `v2.7.0`

## Run Context

| Parameter | Value |
|---|---|
| Backend | vllm |
| Server | `http://***:30000/v1` |
| Model (API) | `glm53` |
| Model (Root) | `local-inference-lab/GLM-5.3-Flash-NVFP4` |
| Temperature | 0.0 |
| Seed | 42 |
| Max Turns | 8 |
| Timeout | 120.0s |
| Scenarios | all (88) |
| Parallel | 1 (sequential) |
| Error Rate | 0.0 |
| Thinking | enabled |
| Max Tokens | 16384 |

## Inference Engine

| Property | Value |
|---|---|
| Engine | vLLM 0.26.1rc0+glm53.r39.vllm9e5d1793 |
| Max Model Length | 524,288 |
| Host | `localhost` |
| Platform | `macOS-26.6.2-arm64-arm-64bit-Mach-O` |
| Python | 3.14.7 |

## Results

| Test | pp t/s | tg t/s | TTFT (ms) | Total (ms) | Tokens |
|---|---:|---:|---:|---:|---:|
| pp2048 tg128 @ d0 | 2,103 | 61.5 | 900 | 2,933 | 2048+128 |
| pp2048 tg128 @ d0 c2 | 2,157 | 64.9 | 1,279 | 4,557 | 2048+128 |
| pp2048 tg128 @ d4096 | 2,502 | 53.5 | 2,266 | 4,609 | 2048+128 |
| pp2048 tg128 @ d4096 c2 | 2,410 | 67.0 | 4,135 | 7,314 | 2048+128 |
| pp2048 tg128 @ d8192 | 2,570 | 54.0 | 3,546 | 5,868 | 2048+128 |
| pp2048 tg128 @ d8192 c2 | 2,504 | 60.2 | 6,540 | 9,709 | 2048+128 |