Ollama (Inference Runtime)open-weight
Released: 2025-01-22

Ollama DeepSeek-R1 (Q4_K_M)

Frontier reasoning model packaged for local cluster execution using Ollama GGUF sharding.

Intelligence Index
90.1/ 100
Calibrated multi-domain composite
Throughput Speed
24tok/sec
Output streaming throughput
Time To First Token
850ms
Initial chunk server latency
LiveBench Contam-Free
80.0%
September 2026 suite score

Sourced Benchmark Evaluations (2)

Verified performance across authoritative benchmarks with provenance tracking.
BenchmarkStatusScoreTrustDateSource TypeProvenance
ARC-AGI-2Nearing Saturation71.4%
75
2025-02-19independentSource ↗
SWE-bench VerifiedSaturated64.6%
25
2025-01-31independentSource ↗
Local Hardware Execution (Ollama)Hardware Compatible
# 1. Pull and execute model locally with Ollama
ollama run ollama-deepseek-r1-q4

# 2. Or invoke via local OpenAI-compatible endpoint
curl http://localhost:11434/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "ollama-deepseek-r1-q4",
    "messages": [{"role": "user", "content": "Analyze reasoning chains on AIME 2026"}]
  }'

Evaluation & Sourcing Notes

Scores listed for Ollama DeepSeek-R1 (Q4_K_M) represent verified evaluations extracted from official research papers, independent evaluation suites (HELM, LMSYS, OpenCompass, LiveBench), and verified audit reports.

All benchmarks marked as saturated or deprecated reflect historical performance where the benchmark no longer provides active discriminative power.