Qwen3.8-27B · IQ1_S
This page aggregates 1 real-world runs of Qwen3.8-27B (IQ1_S) on NVIDIA RTX PRO 6000 Blackwell 96GB with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
182.59 tok/s
Decode
Decode speed
968.64 tok/s
Prefill
Prefill speed
1.78 s
TTFT
Time to first token
25.91 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 (current)Decode 182.59 · Prefill 968.64 ·
- Ollama · Q6_K 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)
- 182.59 tok/s
- Prefill (avg)
- 968.64 tok/s
- TTFT (avg)
- 1.78 s
- VRAM (avg)
- 25.91 GB
- MTP acceptance rate
- —
- TTFB
- 1.46 GB
- Power draw
- 374.3 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.8-27B
- Quantization
- IQ1_S
- Framework
- Ollama
- Version
- v0.21
- Context length
- 2048 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
- NVIDIA RTX PRO 6000 Blackwell 96GB
- Nominal VRAM
- 96 GB
- Measured VRAM (avg)
- 25.91 GB
- OS
- Windows 11 23H2
- Driver
- 560.94
- CUDA
- 12.8
- Power draw
- 374.3 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
v0.21 · Windows 11 23H2 · CUDA 12.8 · 2048 ctx
182.59 tok/s
Decode
968.64 tok/s
Prefill
1.78 s
TTFT
25.91 GB
VRAM
—
MTP
374.3 W
Power draw
L2 batch seed 2026-10-19: Ollama on hw_id=68 running model_id=5 at IQ1_S