Back to search results
Kimi-K3 · Q5_K_M
NVIDIA RTX 507012GBSGLang 0.4.4L0 Self-reported
This page aggregates 1 real-world runs of Kimi-K3 (Q5_K_M) on NVIDIA RTX 5070 with SGLang, contributed by 1 independent source platforms; metrics are averages of published measurements.
— tok/s
Decode
Decode speed
— tok/s
Prefill
Prefill speed
— s
TTFT
Time to first token
— GB
VRAM
VRAM usage
L0 Self-reported
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
No published records for this metric under the same model + hardware yet
Core figures
- Decode (avg)
- — tok/s
- Prefill (avg)
- — tok/s
- TTFT (avg)
- — s
- VRAM (avg)
- — GB
- MTP acceptance rate
- —
- TTFB
- — GB
- Power draw
- — W
Configuration
Member-level fields are taken from the most recent run
- Model
- Kimi-K3
- Quantization
- Q5_K_M
- Framework
- SGLang
- Version
- 0.4.4
- Context length
- 4096 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 5070
- Nominal VRAM
- 12 GB
- OS
- Linux
- Driver
- 570.65
- CUDA
- 12.6
Sources & evidence
1 measured records in total, each traceable to its original source
0.4.4 · Linux · CUDA 12.6 · 4096 ctx
— tok/s
Decode
— tok/s
Prefill
— s
TTFT
0 GB
VRAM
—
MTP
— W
Power draw
L0 理论估算（add-500-records-batch2）