Back to search results
Kimi-K3 · Q5_K_M
NVIDIA RTX 507012GBStrata v0.23L2 Cross-framework verified
This page aggregates 1 real-world runs of Kimi-K3 (Q5_K_M) on NVIDIA RTX 5070 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
76.48 tok/s
Decode
Decode speed
397.87 tok/s
Prefill
Prefill speed
2.03 s
TTFT
Time to first token
1.05 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- vLLM · Q3_K_L Decode 76.49 · Prefill 291.62 ·
- Strata · Q5_K_M (current)Decode 76.48 · Prefill 397.87 ·
- SGLang · Q5_K_M Decode — · Prefill — ·
- SGLang · Q4_K_M Decode — · Prefill — ·
- vLLM · Q5_K_M Decode — · Prefill — ·
- vLLM · Q4_K_M Decode — · Prefill — ·
Core figures
- Decode (avg)
- 76.48 tok/s
- Prefill (avg)
- 397.87 tok/s
- TTFT (avg)
- 2.03 s
- VRAM (avg)
- 1.05 GB
- MTP acceptance rate
- 0.66
- TTFB
- 0.61 GB
- Power draw
- 229.7 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Kimi-K3
- Quantization
- Q5_K_M
- Framework
- Strata
- Version
- v0.23
- Context length
- 32768 tokens
- Batch size
- 512
- GPU layers
- 5
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX 5070
- Nominal VRAM
- 12 GB
- Measured VRAM (avg)
- 1.05 GB
- OS
- Ubuntu 24.04
- Driver
- 572.83
- CUDA
- 12.6
- Power draw
- 229.7 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.23 · Ubuntu 24.04 · CUDA 12.6 · 32768 ctx
76.48 tok/s
Decode
397.87 tok/s
Prefill
2.03 s
TTFT
1.05 GB
VRAM
0.66
MTP
229.7 W
Power draw
L2 batch seed 2026-10-18: Strata on hw_id=18 running model_id=73 at Q5_K_M