Back to search results
Qwen3.5-4B · Q5_K_M
NVIDIA RTX 309024GBOllama v0.49L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-4B (Q5_K_M) on NVIDIA RTX 3090 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
80.28 tok/s
Decode
Decode speed
423.81 tok/s
Prefill
Prefill speed
0.11 s
TTFT
Time to first token
9.91 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
17 days ago
Last verified
Performance
- llama.cpp · Q2_K Decode 137.84 · Prefill 685.72 ·
- llama.cpp · Q3_K_S Decode 115.05 · Prefill 556.74 ·
- Ollama · Q3_K_M Decode 101.46 · Prefill 355.86 ·
- Ollama · Q5_K_M (current)Decode 80.28 · Prefill 423.81 ·
- Ollama · Q3_K_S Decode 109.99 · Prefill 558.1 ·
- Ollama · Q8_0 Decode 62.23 · Prefill 337.34 ·
- Strata · IQ4_XS Decode 157.12 · Prefill 630.97 ·
- llama.cpp · Q5_K_S Decode 139.06 · Prefill 548.16 ·
- llama.cpp · Q6_K Decode 108.41 · Prefill 420.36 ·
- vLLM · Q5_K_S Decode 129.61 · Prefill 696.02 ·
Core figures
- Decode (avg)
- 80.28 tok/s
- Prefill (avg)
- 423.81 tok/s
- TTFT (avg)
- 0.11 s
- VRAM (avg)
- 9.91 GB
- MTP acceptance rate
- —
- TTFB
- 0.64 GB
- Power draw
- 335 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-4B
- Quantization
- Q5_K_M
- Framework
- Ollama
- Version
- v0.49
- Context length
- 4096 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
- NVIDIA RTX 3090
- Nominal VRAM
- 24 GB
- Measured VRAM (avg)
- 9.91 GB
- OS
- Ubuntu 24.04
- Driver
- 570.86
- CUDA
- 12.6
- Power draw
- 335 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.49 · Ubuntu 24.04 · CUDA 12.6 · 4096 ctx
80.28 tok/s
Decode
423.81 tok/s
Prefill
0.11 s
TTFT
9.91 GB
VRAM
—
MTP
335 W
Power draw
L2 batch seed 2026-10-19: Ollama on hw_id=2 running model_id=48 at Q5_K_M