Back to search results
Qwen3-8B · IQ1_S
NVIDIA RTX 507012GBllama.cpp v0.53L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-8B (IQ1_S) on NVIDIA RTX 5070 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
116.33 tok/s
Decode
Decode speed
578.18 tok/s
Prefill
Prefill speed
0.45 s
TTFT
Time to first token
9.16 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- llama.cpp · IQ1_S (current)Decode 116.33 · Prefill 578.18 ·
- llama.cpp · Q3_K_M Decode 92.37 · Prefill 403.56 ·
- llama.cpp · IQ2_XS Decode 93.24 · Prefill 441.9 ·
- llama.cpp · Q3_K_S Decode 83.47 · Prefill 327.27 ·
- Strata · IQ3_XS Decode 128.34 · Prefill 480.77 ·
- llama.cpp · Q8_0 Decode 60.9 · Prefill 456.8 ·
- llama.cpp · Q5_K_M Decode 88.8 · Prefill 666 ·
- llama.cpp · Q4_K_M Decode 107 · Prefill 802.5 ·
Core figures
- Decode (avg)
- 116.33 tok/s
- Prefill (avg)
- 578.18 tok/s
- TTFT (avg)
- 0.45 s
- VRAM (avg)
- 9.16 GB
- MTP acceptance rate
- —
- TTFB
- 0.93 GB
- Power draw
- 234.5 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-8B
- Quantization
- IQ1_S
- Framework
- llama.cpp
- Version
- v0.53
- Context length
- 16384 tokens
- Batch size
- 256
- GPU layers
- 20
- 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)
- 9.16 GB
- OS
- Ubuntu 22.04
- Driver
- 565.57
- CUDA
- 13.0
- Power draw
- 234.5 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.53 · Ubuntu 22.04 · CUDA 13.0 · 16384 ctx
116.33 tok/s
Decode
578.18 tok/s
Prefill
0.45 s
TTFT
9.16 GB
VRAM
—
MTP
234.5 W
Power draw
L2 batch seed 2026-10-18: llama.cpp on hw_id=18 running model_id=53 at IQ1_S