Qwen3.8-27B · Q8_0
This page aggregates 1 real-world runs of Qwen3.8-27B (Q8_0) on NVIDIA RTX Spark with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
6.14 tok/s
Decode
Decode speed
31.39 tok/s
Prefill
Prefill speed
1.35 s
TTFT
Time to first token
67.3 GB
VRAM
VRAM usage
1
Measured runs
1
Independent sources
Other
Source platforms
16 days ago
Last verified
Performance
- llama.cpp · Q5_K_M Decode 8.81 · Prefill 37.51 ·
- llama.cpp · Q8_0 Decode 6.42 · Prefill 24.36 ·
- Ollama · Q5_K_M Decode 7.6 · Prefill 28.29 ·
- Ollama · Q6_K Decode 7.47 · Prefill 38.07 ·
- Ollama · Q8_0 (current)Decode 6.14 · Prefill 31.39 ·
- llama.cpp · Q4_K_M Decode 10.59 · Prefill 58.05 ·
- Ollama · Q4_K_M Decode 9.3 · Prefill 41.72 ·
- Ollama · Q4_K_S Decode 9.16 · Prefill 49.98 ·
Core figures
- Decode (avg)
- 6.14 tok/s
- Prefill (avg)
- 31.39 tok/s
- TTFT (avg)
- 1.35 s
- VRAM (avg)
- 67.3 GB
- MTP acceptance rate
- —
- TTFB
- 0.05 GB
- Power draw
- 68.4 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.8-27B
- Quantization
- Q8_0
- Framework
- Ollama
- Version
- v0.37
- Context length
- 16384 tokens
- Batch size
- 512
- GPU layers
- 33
- Flash Attention
- Off
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)
- 67.3 GB
- OS
- Ubuntu 24.04
- Driver
- 615.78
- CUDA
- 13.0
- Power draw
- 68.4 W
- Reference price
- $2,399 · updated 2026-10-19
Prices are not live; check the store page
Get started
Original model resources
Base model resources may not match this quantization. Use the verified deployment weights above when available.
Sources & evidence
1 measured records in total, each traceable to its original source
v0.37 · Ubuntu 24.04 · CUDA 13.0 · 16384 ctx
6.14 tok/s
Decode
31.39 tok/s
Prefill
1.35 s
TTFT
67.3 GB
VRAM
—
MTP
68.4 W
Power draw
L2 batch seed 2026-10-20 (Linux 116GiB unlock): Ollama on Spark running model_id=5 at Q8_0