Flint-40B-A2.5B · Q4_K_S
This page aggregates 1 real-world runs of Flint-40B-A2.5B (Q4_K_S) on AMD Ryzen AI Max+ 395 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
63.8 tok/s
Decode
Decode speed
213.74 tok/s
Prefill
Prefill speed
2.31 s
TTFT
Time to first token
67.29 GB
VRAM
VRAM usage
1
Measured runs
1
Independent sources
Other
Source platforms
14 days ago
Last verified
Performance
- llama.cpp · IQ3_XS Decode 77.09 · Prefill 382.38 ·
- vLLM · Q4_K_S (current)Decode 63.8 · Prefill 213.74 ·
Core figures
- Decode (avg)
- 63.8 tok/s
- Prefill (avg)
- 213.74 tok/s
- TTFT (avg)
- 2.31 s
- VRAM (avg)
- 67.29 GB
- MTP acceptance rate
- —
- TTFB
- 0.51 GB
- Power draw
- 55 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Flint-40B-A2.5B
- Quantization
- Q4_K_S
- Framework
- vLLM
- Version
- v0.47
- Context length
- 2048 tokens
- Batch size
- 32
- GPU layers
- 999
- Flash Attention
- Off
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- AMD Ryzen AI Max+ 395
- Nominal VRAM
- 128 GB
- Measured VRAM (avg)
- 67.29 GB
- OS
- Ubuntu 22.04
- Driver
- amdgpu 6.11
- CUDA
- 12.8
- Power draw
- 55 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
v0.47 · Ubuntu 22.04 · CUDA 12.8 · 2048 ctx
63.8 tok/s
Decode
213.74 tok/s
Prefill
2.31 s
TTFT
67.29 GB
VRAM
—
MTP
55 W
Power draw
L2 batch seed 2026-10-22: vLLM on hw_id=24 running model_id=92 at Q4_K_S