GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
simaai
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
simaai
Model Tree
Qwen/Qwen3-VL-8B-Instruct
Input Modalities
Output Modalities
Supported Functionality
| Component | Method | Weight format | Effective targets |
|---|---|---|---|
Decoder Linear layers and lm_head | GPTQ | symmetric INT4, group size 256, static act-order | 253 |
| Vision encoder Linear layers | GPTQ | symmetric INT8, per-channel, static act-order | 116 |
| Projector/architecture exceptions | none | source BF16 | Explicitly recorded in recipe.yaml |
The lm_head follows the default GPTQ INT4/G256 policy; no INT8 escalation was made. Calibration used lmms-lab/flickr30k test[:512], deterministic dataset order, 512 image-text samples, sequence length 2048, batch size 1, no concatenation, and no padding to maximum length. The exact target names and effective settings are saved in recipe.yaml.
Full MMStar used all 1,500 examples, VLMEvalKit commit 7055d3010c38ccb5dcae1bc9535ca19c7fe5d79f, deterministic generation, and exact_matching without an API judge.
| Checkpoint | Overall accuracy |
|---|---|
| Source | 48.2000% |
| Quantized | 51.3333% |
| Absolute change | 3.1333 percentage points |
| Relative change | 6.5007% |
Evaluation date: 2026-07-16. Slurm jobs: source 4657, quantized 4658. The aggregate evidence row is stored in vlmeval_results/mmstar_results.csv; raw predictions and status files remain under vlmeval_results/mmstar_full/.
Validation: MMStar inference passed (1,500/1,500).
Full matched WikiText-2 word perplexity (EleutherAI/wikitext_document_level, wikitext-2-raw-v1, no example limit; 2026-07-18): source 11.3805; this checkpoint 12.2893; absolute degradation +0.9089; relative degradation +7.99%. Raw JSON evidence: perplexity_results/vlm_full_wikitext/qwen3_vl_8b_{source,gptq_w4g256_visiongptq_w8}_v3.json.
This directory contains the exact quantize.py, recipe.yaml, and versions.txt used for the artifact:
bash
python quantize.py \--model-path /path/to/source-model \--output-dir /path/to/new-quantized-model
text
Python: 3.13.2torch: 2.11.0+cu128CUDA: 12.8transformers: 5.10.1llm-compressor: 0.12.0auto-round: 0.13.0compressed-tensors: 0.17.1
This is the pre-LLiMa quantized Hugging Face artifact. LLiMa compiler output must remain a separate deployment artifact unless its format and redistribution are approved. No Hugging Face upload is authorized for this batch.
Quantization quality can vary by language, visual domain, prompt format, context length, and downstream runtime. The MMStar result does not replace application-specific validation. Audio components, when present, and explicitly excluded projectors remain in source precision as documented in recipe.yaml.