Qwen3.5-0.8B · Q8_0
This page aggregates 1 real-world runs of Qwen3.5-0.8B (Q8_0) on NVIDIA RTX Spark with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
76.23 tok/s
Decode
Decode speed
286.92 tok/s
Prefill
Prefill speed
2.87 s
TTFT
Time to first token
4.03 GB
VRAM
VRAM usage
1
Measured runs
1
Independent sources
Other
Source platforms
15 days ago
Last verified
Performance
- llama.cpp · Q6_K Decode 94.74 · Prefill 304.72 ·
- llama.cpp · Q8_0 (current)Decode 76.23 · Prefill 286.92 ·
- Ollama · FP16 Decode 57.1 · Prefill 306 ·
- Ollama · Q8_0 Decode 79.06 · Prefill 361.81 ·
- llama.cpp · Q4_K_M Decode 129.1 · Prefill 701.36 ·
- llama.cpp · Q5_K_M Decode 99.17 · Prefill 509.83 ·
- Ollama · Q4_K_M Decode 109.43 · Prefill 483.78 ·
Core figures
- Decode (avg)
- 76.23 tok/s
- Prefill (avg)
- 286.92 tok/s
- TTFT (avg)
- 2.87 s
- VRAM (avg)
- 4.03 GB
- MTP acceptance rate
- —
- TTFB
- 0.61 GB
- Power draw
- 50.8 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-0.8B
- Quantization
- Q8_0
- Framework
- llama.cpp
- Version
- v0.54
- Context length
- 16384 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 Spark
- Nominal VRAM
- 128 GB
- Measured VRAM (avg)
- 4.03 GB
- OS
- Ubuntu 24.04
- Driver
- 615.78
- CUDA
- 13.0
- Power draw
- 50.8 W
- Reference price
- $2,399 · updated 2026-10-19
Prices are not live; check the store page
Sources & evidence
1 measured records in total, each traceable to its original source
v0.54 · Ubuntu 24.04 · CUDA 13.0 · 16384 ctx
76.23 tok/s
Decode
286.92 tok/s
Prefill
2.87 s
TTFT
4.03 GB
VRAM
—
MTP
50.8 W
Power draw
L2 batch seed 2026-10-20 (Linux 116GiB unlock): llama.cpp on Spark running model_id=51 at Q8_0