Back to search results
Llama-3.2-3B-Instruct · Q3_K_L
NVIDIA RTX 507012GBOllama v0.37L2 Cross-framework verified
This page aggregates 1 real-world runs of Llama-3.2-3B-Instruct (Q3_K_L) on NVIDIA RTX 5070 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
203.4 tok/s
Decode
Decode speed
838.81 tok/s
Prefill
Prefill speed
2.06 s
TTFT
Time to first token
6.64 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- llama.cpp · IQ4_XS Decode 238.16 · Prefill 793.59 ·
- llama.cpp · Q5_K_S Decode 193.78 · Prefill 821.91 ·
- Ollama · FP16 Decode 100.33 · Prefill 407.38 ·
- Ollama · Q3_K_L (current)Decode 203.4 · Prefill 838.81 ·
- llama.cpp · Q8_0 Decode 163.8 · Prefill 1228.5 ·
- llama.cpp · Q5_K_M Decode 238.3 · Prefill 1787.3 ·
- llama.cpp · Q4_K_M Decode 291.2 · Prefill 2184 ·
Core figures
- Decode (avg)
- 203.4 tok/s
- Prefill (avg)
- 838.81 tok/s
- TTFT (avg)
- 2.06 s
- VRAM (avg)
- 6.64 GB
- MTP acceptance rate
- —
- TTFB
- 1.63 GB
- Power draw
- 242.4 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Llama-3.2-3B-Instruct
- Quantization
- Q3_K_L
- Framework
- Ollama
- Version
- v0.37
- Context length
- 32768 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 5070
- Nominal VRAM
- 12 GB
- Measured VRAM (avg)
- 6.64 GB
- OS
- Windows 11 24H2
- Driver
- 572.83
- CUDA
- 12.6
- Power draw
- 242.4 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.37 · Windows 11 24H2 · CUDA 12.6 · 32768 ctx
203.4 tok/s
Decode
838.81 tok/s
Prefill
2.06 s
TTFT
6.64 GB
VRAM
—
MTP
242.4 W
Power draw
L2 batch seed 2026-10-18: Ollama on hw_id=18 running model_id=70 at Q3_K_L