ibm-granite / text-generation updated 9 months ago

granite-4.0-h-small

Name: granite-4.0-h-small
Author: ibm-granite

📣 Update [10-07-2025]: Added a default system prompt to the chat template to guide the model towards more professional, accurate, and safe responses.

Params

32.2 B

Context

131,072

Downloads 30d

160 K

Likes

308

Commercial use: allowed apache-2.0 Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 10 days

192 K160 K

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	bf16	64.4 GB	76.2 GB	❌ Won’t fit
model.safetensors (bf16, full)	bf16 + 128K ctx	64.4 GB	148.7 GB	❌ Won’t fit

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub

~ · curl · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/granite-4-0-h-small
{
  "hf_id": "ibm-granite/granite-4.0-h-small",
  "params_b": 32.21,
  "context_length": 131072,
  "license": { "id": "apache-2.0", "commercial": "yes" },
  "downloads_30d": 159832,
  "vram_estimates": [
    { "quant": "bf16", "gb": 76.2 }
  ],
  "updated_at": "2026-07-28T18:08:16Z"
}

est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture: GraniteMoeHybridForCausalLM
Parameters: 32.2 B
Tensor type: BF16
Context length: 131,072
Vocabulary: 100,352
Layers / heads: 40 / 32
Licence: apache-2.0
First seen on the Hub: 2025-09-16
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Compare with

Qwen3-8B 16.3 M Qwen3.6-35B-A3B-NVFP4 11.3 M gpt-oss-20b 8.6 M Qwen3-32B 8.3 M dolphin-2.9.1-yi-1.5-34b 4.6 M OTel-2.0-LLM-31B-IT 3.3 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB