Inference
EN
IBM

Granite-4.0-350M

Granite-4.0-350M is a standard model from IBM in the Granite 4.0 350M family. 12 benchmarks count toward its index, in 7 categories.

  • Open weights
  • Standard
  • Input: text
  • Released 2025-10
RankedEnough results for an index.
IndexAll categories, out of 100.11.9±5.7Median 51.0
CoverageIndex weight that has results.90%
SpeedOutput tokens per second.—Median 67/s
First tokenSeconds to the first output token.—Median 1.3 s
Input / 1MUS dollars per 1M input tokens.—Median $0.60
Output / 1MUS dollars per 1M output tokens.—Median $2.55
ContextMaximum tokens in one request.32KMedian 262K
EloLMArena rating and rank.—Median 1422

Run locally

0.35B parameters
16-bit
1.7 GB
8-bit
1.4 GB
4-bit
1.2 GB
Weights
Hugging Face (opens in a new tab) ↗

Memory need with a short context. The 4-bit copy fits in 8 GB. Compare local models

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.1 counted11.5—
CodingCode writing and repair.1 counted5.0—
ReasoningLogic problems and puzzles.2 counted22.1222 / 227
MultimodalTasks with images and text.None counted——
KnowledgeFacts and expert knowledge.4 counted11.2266 / 268
MultilingualTasks in many languages.1 counted5.0—
InstructionTasks with strict prompt rules.2 counted5.063 / 63
MathMath problems.1 counted9.1—

Results

12 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
Critical Physics TasksReasoning0.0%150 / 214
Artificial Analysis Humanity's Last ExamKnowledge5.5%172 / 222
Artificial Analysis Long Context ReasoningReasoning0.0%204 / 217
Evaluating Large Language Models Trained on CodeCoding39.0%21 / 22
τ²-Bench Tool-Agent-User EvaluationAgentic13.2%143 / 149
OTIS Mock AIME 2024-2025Math0.3% ±0.3198 / 200
Artificial Analysis GPQA DiamondKnowledge26.1%198 / 199
GPQA diamond · Epoch AIKnowledge11.2% ±0.9216 / 217
Instruction-Following EvalInstruction55.4%70 / 70
Massive Multitask Language UnderstandingKnowledge35.0%34 / 34
Graduate-Level Google-Proof Q&AKnowledge24.1%141 / 141
Artificial Analysis IFBenchInstruction15.9%146 / 146
Multilingual Grade School MathMultilingual14.7%13 / 13
Massive Multitask Language Understanding ProfessionalKnowledge12.1%75 / 75
BIG-Bench HardReasoning33.1%—

Sources

BenchLMCC BY-NC 4.0Epoch AICC BY

History

5 releases
Index12.2 → 11.9
23 Oct 202612 Nov 2026

Questions

How good is Granite-4.0-350M?
Its index is 11.9 out of 100. That is place 283 of 283 ranked models.
What is Granite-4.0-350M best at?
Reasoning: 22.1 out of 100, place 222 of 227.
What is the context window of Granite-4.0-350M?
32K tokens.
Is Granite-4.0-350M open source?
Yes. Its weights are published.
When was Granite-4.0-350M released?
October 2025.

Badge

Granite-4.0-350M on Inference360: place 283 of 283, index 11.9
HTML
<a href="https://inference360.ai/models/granite-4-0-350m"><img src="https://inference360.ai/badges/granite-4-0-350m.svg" alt="Granite-4.0-350M on Inference360: place 283 of 283, index 11.9" height="20"></a>
Markdown
[![Granite-4.0-350M on Inference360: place 283 of 283, index 11.9](https://inference360.ai/badges/granite-4-0-350m.svg)](https://inference360.ai/models/granite-4-0-350m)

Compare with

Granite-4.0-H-350M12.7MiniCPM5-1B15.5Granite 4.2 30B41.6

More from IBM

All models
Granite-4.0-H-1B16.3Granite-4.0-H-350M12.7Granite-4.0-1BUnrankedGranite 4.2 30B41.6Granite 4.2 8B37.6