Back to search results
DeepSeek-R1-Distill-Qwen-14B · Q3_K_M
AMD Ryzen AI Max+ 395128GBOllama v0.35L2 Cross-framework verified
This page aggregates 1 real-world runs of DeepSeek-R1-Distill-Qwen-14B (Q3_K_M) on AMD Ryzen AI Max+ 395 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
77.2 tok/s
Decode
Decode speed
347.81 tok/s
Prefill
Prefill speed
0.8 s
TTFT
Time to first token
22.09 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- Ollama · Q3_K_M (current)Decode 77.2 · Prefill 347.81 ·
Core figures
- Decode (avg)
- 77.2 tok/s
- Prefill (avg)
- 347.81 tok/s
- TTFT (avg)
- 0.8 s
- VRAM (avg)
- 22.09 GB
- MTP acceptance rate
- —
- TTFB
- 0.62 GB
- Power draw
- 88.9 W
Configuration
Member-level fields are taken from the most recent run
- Model
- DeepSeek-R1-Distill-Qwen-14B
- Quantization
- Q3_K_M
- Framework
- Ollama
- Version
- v0.35
- Context length
- 16384 tokens
- Batch size
- 512
- GPU layers
- 28
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- AMD Ryzen AI Max+ 395
- Nominal VRAM
- 128 GB
- Measured VRAM (avg)
- 22.09 GB
- OS
- Windows 11 23H2
- Driver
- AMD Adrenalin 25.10.1
- CUDA
- N/A
- Power draw
- 88.9 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.35 · Windows 11 23H2 · CUDA N/A · 16384 ctx
77.2 tok/s
Decode
347.81 tok/s
Prefill
0.8 s
TTFT
22.09 GB
VRAM
—
MTP
88.9 W
Power draw
L2 batch seed 2026-10-13: Ollama on hw_id=24 running model_id=71 at Q3_K_M