Back to search results
Qwen3.8-9B · Q8_0
NVIDIA RTX 309024GBllama.cpp v0.35L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.8-9B (Q8_0) on NVIDIA RTX 3090 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
44.9 tok/s
Decode
Decode speed
150.43 tok/s
Prefill
Prefill speed
1.34 s
TTFT
Time to first token
22.8 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
16 days ago
Last verified
Performance
- llama.cpp · IQ2_XS Decode 104.18 · Prefill 429.42 ·
- llama.cpp · Q8_0 (current)Decode 44.9 · Prefill 150.43 ·
- Strata · IQ3_XS Decode 134.6 · Prefill 685.06 ·
- Strata · Q3_K_L Decode 103.74 · Prefill 393.26 ·
- llama.cpp · Q3_K_L Decode 79.17 · Prefill 416.87 ·
- Ollama · Q5_K_S Decode 58.86 · Prefill 223.43 ·
- Ollama · Q8_0 Decode 46.15 · Prefill 154.63 ·
- llama.cpp · Q3_K_S Decode 130.89 · Prefill 575.17 ·
- Ollama · IQ4_XS Decode 98.13 · Prefill 496.33 ·
Core figures
- Decode (avg)
- 44.9 tok/s
- Prefill (avg)
- 150.43 tok/s
- TTFT (avg)
- 1.34 s
- VRAM (avg)
- 22.8 GB
- MTP acceptance rate
- —
- TTFB
- 0.36 GB
- Power draw
- 302.2 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.8-9B
- Quantization
- Q8_0
- Framework
- llama.cpp
- Version
- v0.35
- Context length
- 32768 tokens
- Batch size
- 256
- GPU layers
- 28
- Flash Attention
- Off
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX 3090
- Nominal VRAM
- 24 GB
- Measured VRAM (avg)
- 22.8 GB
- OS
- Windows 11 23H2
- Driver
- 560.94
- CUDA
- 12.4
- Power draw
- 302.2 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.35 · Windows 11 23H2 · CUDA 12.4 · 32768 ctx
44.9 tok/s
Decode
150.43 tok/s
Prefill
1.34 s
TTFT
22.8 GB
VRAM
—
MTP
302.2 W
Power draw
L2 batch seed 2026-10-19: llama.cpp on hw_id=2 running model_id=52 at Q8_0