M3 Max DeepSeek R1 Distill Qwen 32B Q4_K - Medium TTFT (Ollama, siliconscore ref)
2000.0 ms (time to first token)
Fields
id
benchmarks/m3max-deepseek-r1-distill-qwen-32b-q4-k-medium-ollama-ctxnp-ttftMetric
ttft_ms
Value
2,000
Unit
ms (time to first token)
Model
DeepSeek R1 Distill Qwen 32B
Methodology
Silicon Score benchmarks.csv reference run. M3 Max (36 GB): DeepSeek R1 Distill Qwen 32B Q4_K - Medium via Ollama. context_tokens=not published. TTFT seconds.
Measured by
third_party
Reproducible
yes
Thermal state
unknown
notes
siliconscore reference run; source_url=https://llmcheck.net/data/benchmarks.json.
Notes
siliconscore reference run; source_url=https://llmcheck.net/data/benchmarks.json.