Flint-40B-A2.5B · IQ1_S
This page aggregates 1 real-world runs of Flint-40B-A2.5B (IQ1_S) on Apple M5 Ultra with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
324.79 tok/s
Decode
Decode speed
1,453.99 tok/s
Prefill
Prefill speed
1.3 s
TTFT
Time to first token
37.2 GB
VRAM
VRAM usage
1
Measured runs
1
Independent sources
Other
Source platforms
14 days ago
Last verified
Performance
- llama.cpp · IQ1_S (current)Decode 324.79 · Prefill 1453.99 ·
- llama.cpp · Q5_K_S Decode 181.42 · Prefill 831.96 ·
- Ollama · Q2_K Decode 230.73 · Prefill 1077.9 ·
Core figures
- Decode (avg)
- 324.79 tok/s
- Prefill (avg)
- 1,453.99 tok/s
- TTFT (avg)
- 1.3 s
- VRAM (avg)
- 37.2 GB
- MTP acceptance rate
- —
- TTFB
- 2.6 GB
- Power draw
- 113.3 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Flint-40B-A2.5B
- Quantization
- IQ1_S
- Framework
- llama.cpp
- Version
- v0.30
- Context length
- 32768 tokens
- Batch size
- 512
- GPU layers
- 33
- Flash Attention
- Off
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- Apple M5 Ultra
- Nominal VRAM
- 512 GB
- Measured VRAM (avg)
- 37.2 GB
- OS
- macOS 26.1
- Power draw
- 113.3 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
v0.30 · macOS 26.1 · 32768 ctx
324.79 tok/s
Decode
1,453.99 tok/s
Prefill
1.3 s
TTFT
37.2 GB
VRAM
—
MTP
113.3 W
Power draw
L2 batch seed 2026-10-22: llama.cpp on hw_id=29 running model_id=92 at IQ1_S