Flint-40B-A2.5B · IQ4_XS
This page aggregates 1 real-world runs of Flint-40B-A2.5B (IQ4_XS) on Apple M5 Max with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
123.41 tok/s
Decode
Decode speed
650.98 tok/s
Prefill
Prefill speed
1.96 s
TTFT
Time to first token
63.95 GB
VRAM
VRAM usage
1
Measured runs
1
Independent sources
Other
Source platforms
13 days ago
Last verified
Performance
- llama.cpp · Q3_K_M Decode 152.51 · Prefill 687.68 ·
- Ollama · IQ4_XS (current)Decode 123.41 · Prefill 650.98 ·
- Ollama · Q2_K Decode 153.39 · Prefill 803.06 ·
Core figures
- Decode (avg)
- 123.41 tok/s
- Prefill (avg)
- 650.98 tok/s
- TTFT (avg)
- 1.96 s
- VRAM (avg)
- 63.95 GB
- MTP acceptance rate
- —
- TTFB
- 0.99 GB
- Power draw
- 51.6 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Flint-40B-A2.5B
- Quantization
- IQ4_XS
- Framework
- Ollama
- Version
- v0.30
- Context length
- 32768 tokens
- Batch size
- 256
- GPU layers
- 20
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- Apple M5 Max
- Nominal VRAM
- 128 GB
- Measured VRAM (avg)
- 63.95 GB
- OS
- macOS 26.1
- Power draw
- 51.6 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
v0.30 · macOS 26.1 · 32768 ctx
123.41 tok/s
Decode
650.98 tok/s
Prefill
1.96 s
TTFT
63.95 GB
VRAM
—
MTP
51.6 W
Power draw
L2 batch seed 2026-10-22: Ollama on hw_id=28 running model_id=92 at IQ4_XS