Flint-40B-A2.5B · IQ4_XS
This page aggregates 1 real-world runs of Flint-40B-A2.5B (IQ4_XS) on Apple M2 Ultra with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
184.42 tok/s
Decode
Decode speed
830.52 tok/s
Prefill
Prefill speed
1.07 s
TTFT
Time to first token
63.95 GB
VRAM
VRAM usage
1
Measured runs
1
Independent sources
Other
Source platforms
14 days ago
Last verified
Performance
- llama.cpp · Q5_K_S Decode 159.13 · Prefill 607.98 ·
- Ollama · IQ4_XS (current)Decode 184.42 · Prefill 830.52 ·
Core figures
- Decode (avg)
- 184.42 tok/s
- Prefill (avg)
- 830.52 tok/s
- TTFT (avg)
- 1.07 s
- VRAM (avg)
- 63.95 GB
- MTP acceptance rate
- —
- TTFB
- 1.48 GB
- Power draw
- 140.3 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Flint-40B-A2.5B
- Quantization
- IQ4_XS
- Framework
- Ollama
- Version
- v0.31
- Context length
- 2048 tokens
- Batch size
- 512
- GPU layers
- 99
- Flash Attention
- Off
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- Apple M2 Ultra
- Measured VRAM (avg)
- 63.95 GB
- OS
- macOS 26.1
- Power draw
- 140.3 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
v0.31 · macOS 26.1 · 2048 ctx
184.42 tok/s
Decode
830.52 tok/s
Prefill
1.07 s
TTFT
63.95 GB
VRAM
—
MTP
140.3 W
Power draw
L2 batch seed 2026-10-22: Ollama on hw_id=103 running model_id=92 at IQ4_XS