elephant-1 · Q3_K_M
This page aggregates 1 real-world runs of elephant-1 (Q3_K_M) on AMD Radeon RX 7900 XTX with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
94.98 tok/s
Decode
Decode speed
305.39 tok/s
Prefill
Prefill speed
2.11 s
TTFT
Time to first token
14.95 GB
VRAM
VRAM usage
1
Measured runs
1
Independent sources
Other
Source platforms
13 days ago
Last verified
Performance
- vLLM · Q3_K_M (current)Decode 94.98 · Prefill 305.39 ·
Core figures
- Decode (avg)
- 94.98 tok/s
- Prefill (avg)
- 305.39 tok/s
- TTFT (avg)
- 2.11 s
- VRAM (avg)
- 14.95 GB
- MTP acceptance rate
- —
- TTFB
- 0.76 GB
- Power draw
- 246.6 W
Configuration
Member-level fields are taken from the most recent run
- Model
- elephant-1
- Quantization
- Q3_K_M
- Framework
- vLLM
- Version
- v0.32
- Context length
- 4096 tokens
- Batch size
- 16
- GPU layers
- 999
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- AMD Radeon RX 7900 XTX
- Nominal VRAM
- 24 GB
- Measured VRAM (avg)
- 14.95 GB
- OS
- Windows 11 23H2
- Driver
- amdgpu 6.12
- CUDA
- 12.8
- Power draw
- 246.6 W
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
v0.32 · Windows 11 23H2 · CUDA 12.8 · 4096 ctx
94.98 tok/s
Decode
305.39 tok/s
Prefill
2.11 s
TTFT
14.95 GB
VRAM
—
MTP
246.6 W
Power draw
L2 batch seed 2026-10-22: vLLM on hw_id=11 running model_id=95 at Q3_K_M