GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Yash06B
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Yash06B
Model Tree
unsloth/Qwen2.5-1.5B-Instruct
Input Modalities
Output Modalities
Supported Functionality
Execution accuracy = the generated SQL returns the same rows as the gold SQL on the database.
Test set: gold_test (n=50)
| Model | Hardware | Exec. accuracy (95% CI) | Easy / Med / Hard | Valid SQL | p50 latency | p95 latency | Cost / 1k requests |
|---|---|---|---|---|---|---|---|
| Qwen2.5-1.5B QLoRA, Q4_K_M GGUF (ours) | RTX 4050 laptop, Ollama | 62.0% (50-74) | 93 / 70 / 20 | 86% | 2.34s | 2.77s | n/a |
| Qwen2.5-1.5B QLoRA (ours) | Colab T4 (4-bit) | 56.0% (42-70) | 80 / 65 / 20 | 88% | 4.44s | 9.88s | $0.483 |
| Llama 3.2 3B (base, zero-shot) | RTX 4050 laptop, Ollama | 52.0% (38-66) | 80 / 65 / 7 | 86% | 2.59s | 3.29s | n/a |
| Qwen2.5-1.5B-Instruct (base) | Colab T4 (4-bit) | 32.0% (20-44) | 53 / 35 / 7 | 66% | 3.42s | 6.41s | $0.355 |
Test set: test_synth (n=33)
| Model | Hardware | Exec. accuracy (95% CI) | Easy / Med / Hard | Valid SQL | p50 latency | p95 latency | Cost / 1k requests |
|---|---|---|---|---|---|---|---|
| Qwen2.5-1.5B QLoRA, Q4_K_M GGUF (ours) | RTX 4050 laptop, Ollama | 42.4% (24-61) | 67 / 40 / 33 | 91% | 2.54s | 3.03s | n/a |
| Qwen2.5-1.5B QLoRA (ours) | Colab T4 (4-bit) | 39.4% (24-55) | 67 / 47 / 17 | 85% | 6.03s | 9.75s | $0.605 |
| Llama 3.2 3B (base, zero-shot) | RTX 4050 laptop, Ollama | 15.2% (6-27) | 33 / 20 / 0 | 94% | 2.78s | 3.41s | n/a |
| Qwen2.5-1.5B-Instruct (base) | Colab T4 (4-bit) | 12.1% (3-24) | 33 / 7 / 8 | 61% | 4.08s | 6.97s | $0.410 |
model: unsloth/Qwen2.5-1.5B-Instructmax_seq_length: 2048lora_r: 16lora_alpha: 32lora_dropout: 0.0epochs: 3.0lr: 0.0002batch_size: 4grad_accum: 4warmup_ratio: 0.03weight_decay: 0.01scheduler: cosineeval_steps: 10seed: 3407report_to: nonerun_name: Nonesave_merged: Falsemax_steps: -1effective_batch: 16n_train: 340n_val: 20family: qwenThe model expects the system prompt it was trained with (instructions + the full schema). The
Modelfile in the GGUF repo bakes it in, so create the model from it rather than with ollama run hf.co/...:
bash
hf download Yash06B/sql-qwen2.5-1.5b-GGUF --local-dir sql-qwencd sql-qwenollama create sql-qwen -f Modelfileollama run sql-qwen "Which 3 countries have the most customers?"Trained for this one schema only. It will not generalize to arbitrary databases without retraining.
The training data is synthetic (written by qwen2.5-coder:7b and filtered by execution), so it inherits
that model's blind spots. Large API models have not been evaluated on this test set yet.
hf download Yash06B/sql-qwen2.5-1.5b-GGUF --local-dir sql-qwencd sql-qwenollama create sql-qwen -f Modelfileollama run sql-qwen "Which 3 countries have the most customers?"