Qwen3.5-4B · FP16
This page aggregates 1 real-world runs of Qwen3.5-4B (FP16) on NVIDIA RTX Spark with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
40.67 tok/s
Decode
Decode speed
196.29 tok/s
Prefill
Prefill speed
1.02 s
TTFT
Time to first token
17.64 GB
VRAM
VRAM usage
1
Measured runs
1
Independent sources
Other
Source platforms
16 days ago
Last verified
Performance
- llama.cpp · Q4_K_M Decode 90.26 · Prefill 398.49 ·
- llama.cpp · Q5_K_M Decode 71.83 · Prefill 346.83 ·
- llama.cpp · Q8_0 Decode 64.66 · Prefill 241.03 ·
- Ollama · FP16 (current)Decode 40.67 · Prefill 196.29 ·
- Ollama · Q5_K_M Decode 69.06 · Prefill 289.88 ·
- Ollama · Q8_0 Decode 56.21 · Prefill 286.64 ·
- llama.cpp · Q3_K_S Decode 110.57 · Prefill 596.61 ·
- Ollama · Q4_K_M Decode 76.41 · Prefill 245.09 ·
Core figures
- Decode (avg)
- 40.67 tok/s
- Prefill (avg)
- 196.29 tok/s
- TTFT (avg)
- 1.02 s
- VRAM (avg)
- 17.64 GB
- MTP acceptance rate
- —
- TTFB
- 0.33 GB
- Power draw
- 69.9 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-4B
- Quantization
- FP16
- Framework
- Ollama
- Version
- v0.46
- Context length
- 32768 tokens
- Batch size
- 512
- GPU layers
- 99
- 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)
- 17.64 GB
- OS
- Ubuntu 24.04
- Driver
- 615.78
- CUDA
- 13.0
- Power draw
- 69.9 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
v0.46 · Ubuntu 24.04 · CUDA 13.0 · 32768 ctx
40.67 tok/s
Decode
196.29 tok/s
Prefill
1.02 s
TTFT
17.64 GB
VRAM
—
MTP
69.9 W
Power draw
L2 batch seed 2026-10-20 (Linux 116GiB unlock): Ollama on Spark running model_id=48 at FP16