Back to search results
Qwen3.6-35B-A3B · IQ2_M
NVIDIA H100 80GB HBM380GBOllama v0.30L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.6-35B-A3B (IQ2_M) on NVIDIA H100 80GB HBM3 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
321.92 tok/s
Decode
Decode speed
1,762.51 tok/s
Prefill
Prefill speed
1.2 s
TTFT
Time to first token
40.32 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
16 days ago
Last verified
Performance
- vLLM · IQ4_XS Decode 288.72 · Prefill 1282.53 ·
- vLLM · Q3_K_M Decode 355.61 · Prefill 1722.65 ·
- Ollama · IQ2_M (current)Decode 321.92 · Prefill 1762.51 ·
- Ollama · Q8_0 Decode 296.95 · Prefill 1140.84 ·
Core figures
- Decode (avg)
- 321.92 tok/s
- Prefill (avg)
- 1,762.51 tok/s
- TTFT (avg)
- 1.2 s
- VRAM (avg)
- 40.32 GB
- MTP acceptance rate
- —
- TTFB
- 2.58 GB
- Power draw
- 593.1 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.6-35B-A3B
- Quantization
- IQ2_M
- Framework
- Ollama
- Version
- v0.30
- 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 H100 80GB HBM3
- Nominal VRAM
- 80 GB
- Measured VRAM (avg)
- 40.32 GB
- OS
- Ubuntu 24.04
- Driver
- 565.57
- CUDA
- 13.0
- Power draw
- 593.1 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.30 · Ubuntu 24.04 · CUDA 13.0 · 4096 ctx
321.92 tok/s
Decode
1,762.51 tok/s
Prefill
1.2 s
TTFT
40.32 GB
VRAM
—
MTP
593.1 W
Power draw
L2 batch seed 2026-10-19: Ollama on hw_id=55 running model_id=47 at IQ2_M