Back to search results
DeepSeek-V4-Flash · UD-IQ2_XXS
2x NVIDIA RTX 509064GBllama.cpp b10236L0 Self-reported
This page aggregates 1 real-world runs of DeepSeek-V4-Flash (UD-IQ2_XXS) on 2x NVIDIA RTX 5090 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
19.39 tok/s
Decode
Decode speed
692.41 tok/s
Prefill
Prefill speed
0.12 s
TTFT
Time to first token
51.17 GB
VRAM
VRAM usage
L0 Self-reported
1
Measured runs
1
Independent sources
GitHub
Source platforms
Today
Last verified
Performance
- llama.cpp · UD-IQ2_XXS (current)Decode 19.39 · Prefill 692.41 ·
Core figures
- Decode (avg)
- 19.39 tok/s
- Prefill (avg)
- 692.41 tok/s
- TTFT (avg)
- 0.12 s
- VRAM (avg)
- 51.17 GB
- MTP acceptance rate
- —
- TTFB
- — GB
- Power draw
- 415 W
Configuration
Member-level fields are taken from the most recent run
- Model
- DeepSeek-V4-Flash
- Quantization
- UD-IQ2_XXS
- Framework
- llama.cpp
- Version
- b10236
- Context length
- 204800 tokens
- Batch size
- 4096
- GPU layers
- 99
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- 2x NVIDIA RTX 5090
- Nominal VRAM
- 64 GB
- Measured VRAM (avg)
- 51.17 GB
- OS
- Ubuntu 24.04.4 LTS
- Driver
- 610.43.03
- CUDA
- 13.3
- Power draw
- 415 W
Get started
Startup command
Command from the latest benchmark runmodel=/models/deepseek-v4-flash-0731-gguf/UD-IQ2_XXS/DeepSeek-V4-Flash-0731-UD-IQ2_XXS-00001-of-00003.gguf offload=blk\.[0-9]+\.ffn_(gate|up|down)_exps\.weight=CPU threads=16 ubatch=4096 kv=q8_0 ngl=99 split=1,1Sources & evidence
1 measured records in total, each traceable to its original source
b10236 · Ubuntu 24.04.4 LTS · CUDA 13.3 · 204800 ctx
19.39 tok/s
Decode
692.41 tok/s
Prefill
0.12 s
TTFT
51.17 GB
VRAM
—
MTP
415 W
Power draw
[bench] narrative run 1/5: 1000 tok in 52.7s (19.02 decode TPS, ttft 117ms) [bench] narrative run 2/5: 1000 tok in 52.9s (18.95 decode TPS, ttft 116ms) [bench] narrative run 3/5: 1000 tok in 52.2s (19.21 decode TPS, ttft 116ms) [bench] narrative run 4/5: 1000 tok in 49.9s (20.07 decode TPS, ttft 117ms) [bench] narrative run 5/5: 1000 tok in 50.9s (19.69 decode TPS, ttft 116ms)