Back to search results
Qwen3-8B · Q5_K_M
NVIDIA RTX 509032GBOllama v0.26L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-8B (Q5_K_M) on NVIDIA RTX 5090 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
172.9 tok/s
Decode
Decode speed
940.17 tok/s
Prefill
Prefill speed
1.94 s
TTFT
Time to first token
17.72 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- llama.cpp · IQ4_XS Decode 253.29 · Prefill 909.82 ·
- llama.cpp · Q6_K Decode 179.01 · Prefill 827.24 ·
- vLLM · IQ3_S Decode 284.83 · Prefill 1483.72 ·
- vLLM · IQ4_XS Decode 252.51 · Prefill 829.1 ·
- Ollama · Q5_K_M (current)Decode 172.9 · Prefill 940.17 ·
- llama.cpp · Q8_0 Decode 162.5 · Prefill 1218.8 ·
- llama.cpp · Q5_K_M Decode 236.9 · Prefill 1776.8 ·
- llama.cpp · Q4_K_M Decode 285.3 · Prefill 2139.8 ·
Core figures
- Decode (avg)
- 172.9 tok/s
- Prefill (avg)
- 940.17 tok/s
- TTFT (avg)
- 1.94 s
- VRAM (avg)
- 17.72 GB
- MTP acceptance rate
- —
- TTFB
- 1.38 GB
- Power draw
- 552.6 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-8B
- Quantization
- Q5_K_M
- Framework
- Ollama
- Version
- v0.26
- 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 5090
- Nominal VRAM
- 32 GB
- Measured VRAM (avg)
- 17.72 GB
- OS
- macOS 15.0
- Driver
- 565.57
- CUDA
- 12.8
- Power draw
- 552.6 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.26 · macOS 15.0 · CUDA 12.8 · 16384 ctx
172.9 tok/s
Decode
940.17 tok/s
Prefill
1.94 s
TTFT
17.72 GB
VRAM
—
MTP
552.6 W
Power draw
L2 batch seed 2026-10-10: Ollama on hw_id=13 running model_id=53 at Q5_K_M