Back to search results
Qwen3.5-0.8B · Q3_K_S
NVIDIA RTX 409024GBllama.cpp v0.30L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-0.8B (Q3_K_S) on NVIDIA RTX 4090 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
364.6 tok/s
Decode
Decode speed
1,679.71 tok/s
Prefill
Prefill speed
0.33 s
TTFT
Time to first token
3.19 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 Decode 373.87 · Prefill 1737.06 ·
- llama.cpp · Q3_K_S (current)Decode 364.6 · Prefill 1679.71 ·
- vLLM · FP16 Decode 161.03 · Prefill 685.23 ·
- vLLM · IQ1_S Decode 328.9 · Prefill 1532.17 ·
- llama.cpp · IQ2_XS Decode 280.41 · Prefill 1104.34 ·
- llama.cpp · Q4_K_M Decode 278.24 · Prefill 916.88 ·
- vLLM · IQ3_XS Decode 302.65 · Prefill 1148.6 ·
Core figures
- Decode (avg)
- 364.6 tok/s
- Prefill (avg)
- 1,679.71 tok/s
- TTFT (avg)
- 0.33 s
- VRAM (avg)
- 3.19 GB
- MTP acceptance rate
- —
- TTFB
- 2.92 GB
- Power draw
- 304.4 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-0.8B
- Quantization
- Q3_K_S
- Framework
- llama.cpp
- Version
- v0.30
- Context length
- 4096 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 4090
- Nominal VRAM
- 24 GB
- Measured VRAM (avg)
- 3.19 GB
- OS
- Ubuntu 24.04
- Driver
- 570.86
- CUDA
- 12.6
- Power draw
- 304.4 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.30 · Ubuntu 24.04 · CUDA 12.6 · 4096 ctx
364.6 tok/s
Decode
1,679.71 tok/s
Prefill
0.33 s
TTFT
3.19 GB
VRAM
—
MTP
304.4 W
Power draw
L2 batch seed 2026-10-18: llama.cpp on hw_id=1 running model_id=51 at Q3_K_S