Skip to content
Model Pareto

Granite 4.0 350M

IBM GraniteOpen weightsartificialanalysis.ai ↗
Input
—
Output
—
Speed
~110tok/sest.
Context
33Ktokens

Long-tail import from Artificial Analysis (2026-09-24); AA variant: Granite 4.0 350M. Price = AA median host price.

Rankings

Self-hostingEstimated

How we estimate →

What it would cost to run these open weights yourself on rented GPUs. No API sells this model, so this is its price on the chart.

Hardware
1× H200 141GB
BF16 weights
Throughput
~35,399 tok/s
many requests batched
Price
$0.011–0.090 /M tok
busy → light use
On your own machine
RTX 5090 32GB (int4, 300+ tok/s single-stream)
single consumer GPU or Mac
Assumptions (5)
  • BF16 weights (0.35B params) + 25% KV-cache headroom ≈ 1 GB
  • 1× H200 141GB at $3.59–$7.91/GPU-hour on-demand (2026-09-24)
  • ~35,399 output tok/s aggregate at batch 256 (bandwidth-bound)
  • Blended 3:1 input:output; prefill ~667,575 tok/s
  • Low = 75% utilization at the low GPU price; high = 20% at the high price

Benchmark scores

~ italic, dashed = no published score yet, estimated from related benchmarks.

Writing & chat

Hard reasoning

Agents

~#14 of 15 (estimated)~51.0%
  1. #1Kimi K384.8%
  2. #2Qwen3.8 27B84.3%
  3. #13Nemotron 3.5 Super VL51.1%
  4. ~#14Granite 4.0 350MEstimated51.0%
  5. #14Claude Haiku 4.550.7%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~#3 of 5 (estimated)~53.8%
  1. #1GLM-5.3 Flash59.1%
  2. #2Kimi K358.3%
  3. ~#3Granite 4.0 350MEstimated53.8%
  4. #3GPT-5.6 Terra50.2%
No published score — estimated from related benchmarks
BrowseCompEstimated
~#21 of 22 (estimated)~33.0%
  1. #1Atria Dawn Preview92.5%
  2. #2GPT-6 Astra91.5%
  3. #20Nemotron 3 Ultra44.4%
  4. ~#21Granite 4.0 350MEstimated33.0%
  5. #21Mistral Small 421.3%
No published score — estimated from related benchmarks
~#60 of 92 (estimated)~704 Elo
  1. #1Claude Opus 5.51866
  2. #2Muse Wonder Full1857
  3. #59Claude Haiku 4.5719
  4. ~#60Granite 4.0 350MEstimated704
  5. #60MiniCPM5-2B694
No published score — estimated from related benchmarks
~#79 of 85 (estimated)~0.3%
  1. #1Claude Fable 5.276.4%
  2. #2Muse Wonder Full71.3%
  3. #77Granite 4.2 3B0.4%
  4. ~#79Granite 4.0 350MEstimated0.3%
  5. #79gpt-oss-120b0.2%
No published score — estimated from related benchmarks
~last of 91 (estimated)below measured range (<3.3%)
  1. #1Muse Spark 1.350.5%
  2. #2GLM-5.350.3%
  3. #90Llama 4 Scout3.3%
  4. ~#91Granite 4.0 350MEstimated<3.3%
No published score — estimated from related benchmarks