Flint-40B-A2.5B · IQ4_XS
This page aggregates 1 real-world runs of Flint-40B-A2.5B (IQ4_XS) on NVIDIA RTX Spark with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
74.46 tok/s
Decode
Decode speed
328.19 tok/s
Prefill
Prefill speed
0.25 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 · IQ3_S Decode 91.56 · Prefill 457.14 ·
- llama.cpp · Q3_K_S Decode 100.54 · Prefill 475.16 ·
- llama.cpp · Q4_K_M Decode 76.22 · Prefill 300.34 ·
- Ollama · IQ4_XS (current)Decode 74.46 · Prefill 328.19 ·
- Ollama · Q2_K Decode 96.77 · Prefill 510.91 ·
- Ollama · Q4_K_M Decode 70.03 · Prefill 271.9 ·
Core figures
- Decode (avg)
- 74.46 tok/s
- Prefill (avg)
- 328.19 tok/s
- TTFT (avg)
- 0.25 s
- VRAM (avg)
- 63.95 GB
- MTP acceptance rate
- —
- TTFB
- 0.6 GB
- Power draw
- 78.1 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Flint-40B-A2.5B
- Quantization
- IQ4_XS
- Framework
- Ollama
- Version
- v0.24
- Context length
- 32768 tokens
- Batch size
- 256
- GPU layers
- 28
- Flash Attention
- Off
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX Spark
- Nominal VRAM
- 128 GB
- Measured VRAM (avg)
- 63.95 GB
- OS
- Ubuntu 24.04
- Driver
- 615.78
- CUDA
- 13.0
- Power draw
- 78.1 W
- Reference price
- $2,399 · updated 2026-10-19
Prices are not live; check the store page
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
v0.24 · Ubuntu 24.04 · CUDA 13.0 · 32768 ctx
74.46 tok/s
Decode
328.19 tok/s
Prefill
0.25 s
TTFT
63.95 GB
VRAM
—
MTP
78.1 W
Power draw
L2 batch seed 2026-10-22: Ollama on hw_id=110 running model_id=92 at IQ4_XS