Qwen3.8-27B · Q6_K
This page aggregates 1 real-world runs of Qwen3.8-27B (Q6_K) on NVIDIA RTX PRO 6000 Blackwell 96GB with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
86.06 tok/s
Decode
Decode speed
324.27 tok/s
Prefill
Prefill speed
2.39 s
TTFT
Time to first token
58.8 GB
VRAM
VRAM usage
1
Measured runs
1
Independent sources
Other
Source platforms
16 days ago
Last verified
Performance
- llama.cpp · Q5_K_S Decode 112.25 · Prefill 455.96 ·
- Ollama · IQ1_S Decode 182.59 · Prefill 968.64 ·
- Ollama · Q6_K (current)Decode 86.06 · Prefill 324.27 ·
- vLLM · FP16 Decode — · Prefill — ·
- vLLM · Q8_0 Decode — · Prefill — ·
- vLLM · Q5_K_M Decode — · Prefill — ·
- llama.cpp · FP16 Decode — · Prefill — ·
- llama.cpp · Q8_0 Decode — · Prefill — ·
- llama.cpp · Q5_K_M Decode — · Prefill — ·
Core figures
- Decode (avg)
- 86.06 tok/s
- Prefill (avg)
- 324.27 tok/s
- TTFT (avg)
- 2.39 s
- VRAM (avg)
- 58.8 GB
- MTP acceptance rate
- —
- TTFB
- 0.69 GB
- Power draw
- 378.1 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.8-27B
- Quantization
- Q6_K
- Framework
- Ollama
- Version
- v0.45
- Context length
- 32768 tokens
- Batch size
- 256
- GPU layers
- 33
- 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 96GB
- Nominal VRAM
- 96 GB
- Measured VRAM (avg)
- 58.8 GB
- OS
- Ubuntu 22.04
- Driver
- 560.94
- CUDA
- 12.6
- Power draw
- 378.1 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 · Ubuntu 22.04 · CUDA 12.6 · 32768 ctx
86.06 tok/s
Decode
324.27 tok/s
Prefill
2.39 s
TTFT
58.8 GB
VRAM
—
MTP
378.1 W
Power draw
L2 batch seed 2026-10-19: Ollama on hw_id=68 running model_id=5 at Q6_K