Qwen3.8-27B · Q2_K
This page aggregates 1 real-world runs of Qwen3.8-27B (Q2_K) on Apple M5 Ultra with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
74.38 tok/s
Decode
Decode speed
283.32 tok/s
Prefill
Prefill speed
1.58 s
TTFT
Time to first token
33.29 GB
VRAM
VRAM usage
1
Measured runs
1
Independent sources
Other
Source platforms
16 days ago
Last verified
Performance
- llama.cpp · IQ2_XS Decode 89.58 · Prefill 565.47 ·
- Ollama · Q2_K (current)Decode 74.38 · Prefill 283.32 ·
- Ollama · Q3_K_S Decode 60.73 · Prefill 250.32 ·
- llama.cpp · Q5_K_M Decode 46.8 · Prefill 351 ·
- llama.cpp · Q4_K_M Decode 57.1 · Prefill 428.3 ·
Core figures
- Decode (avg)
- 74.38 tok/s
- Prefill (avg)
- 283.32 tok/s
- TTFT (avg)
- 1.58 s
- VRAM (avg)
- 33.29 GB
- MTP acceptance rate
- —
- TTFB
- 0.6 GB
- Power draw
- 94.7 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.8-27B
- Quantization
- Q2_K
- Framework
- Ollama
- Version
- v0.45
- Context length
- 4096 tokens
- Batch size
- 256
- 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
- Apple M5 Ultra
- Nominal VRAM
- 512 GB
- Measured VRAM (avg)
- 33.29 GB
- OS
- macOS 26.1
- Power draw
- 94.7 W
Get started
Original model resources
Base model resources may not match this quantization. Use the verified deployment weights above when available.
Sources & evidence
1 measured records in total, each traceable to its original source
v0.45 · macOS 26.1 · 4096 ctx
74.38 tok/s
Decode
283.32 tok/s
Prefill
1.58 s
TTFT
33.29 GB
VRAM
—
MTP
94.7 W
Power draw
L2 batch seed 2026-10-19: Ollama on hw_id=29 running model_id=5 at Q2_K