Downloads · 30 days
382
22% of all-time downloads
Qwen3.5-9B-oQ4e-mtp
mlx-works/Qwen3.5-9B-oQ4e-mtp
Qwen3.5-9B-oQ4e-mtp is a machine learning model from mlx-works. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for mlx.
This model was quantized using oQ (oMLX v0.5.1) mixed-precision quantization.
All-time downloads
1.8K
Public
Parameters
9.7B
6.2 GB on disk
Likes
3
Public
Repo makeup
Click a slice to open those files.
.safetensors6.2 GB · 100%
Parameter types
How the weights are stored.
U329.2B · 95%
Model card
From the Hugging Face model README
Qwen3.5-9B-oQ4e-mtp
This model was quantized using oQ (oMLX v0.5.1) mixed-precision quantization.
Quantization details
- Model type: qwen3_5
- Bits: 4
- Group size: 64
- Format: MLX safetensors
Environment
- Hardware: M5 MacBook Air 32GB
- Inference Framework: oMLX v0.5.1
- Settings:
- Thinking: Disabled
- Chat template parameter: enable_thinking=false (forced)
- TurboQuant KV Cache: Disabled (if enable: reduces speed)
- Native MTP: Enabled (key speed improvement)
Performance Benchmarks
Note: Results are for reference only and may vary depending on hardware, software configuration, and workload.
Single Request Results
| Test | TTFT(ms) | TPOT(ms) | pp TPS | tg TPS | E2E(s) | Throughput | Peak Mem |
|---|---|---|---|---|---|---|---|
| pp1024/tg128 | 1591.5 | 23.16 | 643.4 tok/s | 43.5 tok/s | 4.556 | 252.8 tok/s | 5.96 GB |
| pp4096/tg128 | 5941.8 | 23.44 | 689.4 tok/s | 43.0 tok/s | 8.946 | 472.2 tok/s | 6.58 GB |
Continuous Batching (pp1024 / tg128)
| Batch | tg TPS | Speedup | pp TPS | pp TPS/req | TTFT(ms) | E2E(s) |
|---|---|---|---|---|---|---|
| 1x | 43.5 tok/s | 1.00x | 643.4 tok/s | 643.4 tok/s | 1591.5 | 4.556 |
| 2x | 50.7 tok/s | 1.17x | 641.2 tok/s | 320.6 tok/s | 3193.8 | 8.248 |
| 4x | 81.7 tok/s | 1.88x | 638.1 tok/s | 159.5 tok/s | 6263.5 | 12.683 |
Intelligence Benchmark
Note: Each benchmark round tests only 30 questions. Results are for reference only.
| Benchmark | Accuracy | Correct | Total | Time(s) | Think |
|---|---|---|---|---|---|
| MMLU | 76.7% | 23 | 30 | 34.0 | No |
| TRUTHFULQA | 86.7% | 26 | 30 | 12.4 | No |
| GSM8K | 90.0% | 27 | 30 | 262.0 | No |
| MATHQA | 26.7% | 8 | 30 | 20.5 | No |
| HUMANEVAL | 86.7% | 26 | 30 | 144.9 | No |
Summary
| Benchmark | Accuracy |
|---|---|
| MMLU | 76.7% |
| TRUTHFULQA | 86.7% |
| GSM8K | 90.0% |
| MATHQA | 26.7% |
| HUMANEVAL | 86.7% |
| Average | 73.3% |
- Library
- mlx
- Type
- qwen3_5
- Created
- Jul 11, 2026
- Updated
- Jul 15, 2026