Back to search results
Llama 5 70B · IQ4_XS
NVIDIA RTX 509032GBllama.cpp b4200L0 Self-reported
This page aggregates 1 real-world runs of Llama 5 70B (IQ4_XS) on NVIDIA RTX 5090 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
37 tok/s
Decode
Decode speed
277.5 tok/s
Prefill
Prefill speed
0.36 s
TTFT
Time to first token
32 GB
VRAM
VRAM usage
L0 Self-reported
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- vLLM · IQ3_S Decode 53.6 · Prefill 402 ·
- vLLM · IQ4_XS Decode 40.3 · Prefill 302.3 ·
- vLLM · Q6_K Decode 24.8 · Prefill 186 ·
- vLLM · Q5_K_M Decode 29.3 · Prefill 219.8 ·
- llama.cpp · IQ3_S Decode 49.2 · Prefill 369 ·
- llama.cpp · IQ4_XS (current)Decode 37 · Prefill 277.5 ·
- llama.cpp · Q6_K Decode 22.8 · Prefill 171 ·
- llama.cpp · Q5_K_M Decode 26.9 · Prefill 201.8 ·
- vLLM · Q4_K_M Decode 35.8 · Prefill 268.5 ·
Core figures
- Decode (avg)
- 37 tok/s
- Prefill (avg)
- 277.5 tok/s
- TTFT (avg)
- 0.36 s
- VRAM (avg)
- 32 GB
- MTP acceptance rate
- —
- TTFB
- — GB
- Power draw
- — W
Configuration
Member-level fields are taken from the most recent run
- Model
- Llama 5 70B
- Quantization
- IQ4_XS
- Framework
- llama.cpp
- Version
- b4200
- Context length
- 4096 tokens
- Batch size
- 512
- GPU layers
- 99
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX 5090
- Nominal VRAM
- 32 GB
- Measured VRAM (avg)
- 32 GB
- OS
- Linux
- Driver
- 570.65
- CUDA
- 12.6
Sources & evidence
1 measured records in total, each traceable to its original source
b4200 · Linux · CUDA 12.6 · 4096 ctx
37 tok/s
Decode
277.5 tok/s
Prefill
0.36 s
TTFT
32 GB
VRAM
—
MTP
— W
Power draw
L0 理论估算（add-1000-records-batch3）