ibm-granite / text-generation updated 9 months ago

granite-4.0-h-tiny

Name: granite-4.0-h-tiny
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

6.9 B

Context

131,072

Downloads 30d

292 K

Likes

206

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

Download history

daily snapshots · 10 days

292 K278 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	13.9 GB	16.8 GB	✅ Runs comfortably
model.safetensors (bf16, full)	bf16 + 128K ctx	13.9 GB	32.4 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-tiny
{
  "hf_id": "ibm-granite/granite-4.0-h-tiny",
  "params_b": 6.94,
  "context_length": 131072,
  "license": { "id": "apache-2.0", "commercial": "yes" },
  "downloads_30d": 291998,
  "vram_estimates": [
    { "quant": "bf16", "gb": 16.8 }
  ],
  "updated_at": "2026-07-28T18:06:54Z"
}

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

Specifications

Architecture: GraniteMoeHybridForCausalLM
Parameters: 6.9 B
Tensor type: BF16
Context length: 131,072
Vocabulary: 100,352
Layers / heads: 40 / 12
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 Qwen2.5-7B-Instruct 12.1 M Qwen3.6-35B-A3B-NVFP4 11.3 M Llama-3.1-8B-Instruct 8.0 M Qwen2.5-7B-Instruct-AWQ 4.6 M granite-4.1-8b 4.2 M

Appears in

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