Qwen3.8-27B · Q5_K_M
This page aggregates 1 real-world runs of Qwen3.8-27B (Q5_K_M) on NVIDIA RTX PRO 6000 Blackwell with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
69.9 tok/s
Decode
Decode speed
524.3 tok/s
Prefill
Prefill speed
0.19 s
TTFT
Time to first token
20.5 GB
VRAM
VRAM usage
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- vLLM · FP16 Decode 26.1 · Prefill 195.8 ·
- vLLM · Q8_0 Decode 52.2 · Prefill 391.5 ·
- vLLM · Q5_K_M Decode 76.2 · Prefill 571.5 ·
- llama.cpp · FP16 Decode 24 · Prefill 180 ·
- llama.cpp · Q8_0 Decode 47.9 · Prefill 359.3 ·
- llama.cpp · Q5_K_M (current)Decode 69.9 · Prefill 524.3 ·
- SGLang · NVFP4 Decode 171.1 · Prefill 10877.7 ·
Core figures
- Decode (avg)
- 69.9 tok/s
- Prefill (avg)
- 524.3 tok/s
- TTFT (avg)
- 0.19 s
- VRAM (avg)
- 20.5 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_M
- Framework
- llama.cpp
- Version
- b4200
- 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 PRO 6000 Blackwell
- Nominal VRAM
- 96 GB
- Measured VRAM (avg)
- 20.5 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
b4200 · Linux · CUDA 12.6 · 4096 ctx
69.9 tok/s
Decode
524.3 tok/s
Prefill
0.19 s
TTFT
20.5 GB
VRAM
—
MTP
— W
Power draw
L0 理论估算（add-1000-records-batch3）