Qwen3.8-27B · Q5_K_S
This page aggregates 1 real-world runs of Qwen3.8-27B (Q5_K_S) on NVIDIA RTX 5070 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
36.9 tok/s
Decode
Decode speed
276.8 tok/s
Prefill
Prefill speed
0.36 s
TTFT
Time to first token
12 GB
VRAM
VRAM usage
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- Strata · Q5_K_S (current)Decode 36.9 · Prefill 276.8 ·
- Strata · IQ3_S Decode 61.7 · Prefill 462.8 ·
- Strata · IQ4_XS Decode 46 · Prefill 345 ·
- llama.cpp · Q5_K_S Decode 28.8 · Prefill 216 ·
- llama.cpp · IQ3_S Decode 48.1 · Prefill 360.8 ·
- llama.cpp · IQ4_XS Decode 35.9 · Prefill 269.3 ·
- Strata · IQ2_XS Decode 73.8 · Prefill 553.5 ·
Core figures
- Decode (avg)
- 36.9 tok/s
- Prefill (avg)
- 276.8 tok/s
- TTFT (avg)
- 0.36 s
- VRAM (avg)
- 12 GB
- MTP acceptance rate
- —
- TTFB
- — GB
- Power draw
- — W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.8-27B
- Quantization
- Q5_K_S
- Framework
- Strata
- Version
- 0.5.2
- Context length
- 4096 tokens
- Batch size
- 512
- GPU layers
- 99
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX 5070
- Nominal VRAM
- 12 GB
- Measured VRAM (avg)
- 12 GB
- OS
- Linux
- Driver
- 570.65
- CUDA
- 12.6
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
0.5.2 · Linux · CUDA 12.6 · 4096 ctx
36.9 tok/s
Decode
276.8 tok/s
Prefill
0.36 s
TTFT
12 GB
VRAM
—
MTP
— W
Power draw
L0 理论估算（add-1000-records-batch3）