sbintuitions / text-generation updated 1 year ago

sarashina2.2-0.5b-instruct-v0.1

Model Elyza-tasks-100 Japanese MT Bench English MT Bench ------------------------------------------------------------------------------------------------- --------------- ----------------- ---------------- Qwen/Qwen2.5-0.5B-instruct 1.53 2.95 4.98 sarashina2.2-0.5B-instruct-v0.1 2.38 4.55 5.09 Rakuten/RakutenAI-2.0-mini-instruct 2.41 4.49 5.13 SakanaAI/TinySwallow-1.5B-Instruct 2.81 5.24 6.31 Qwen/Qwen2.5-1.5B-instru...

Params
790 M
Context
8,192
Downloads 30d
248 K
Likes
16
Commercial use: allowed mit Not gated SAFETENSORS 1 languages View on Hugging Face ↗

Download history

daily snapshots · 11 days
251 K220 K
Sep 11Sep 14Sep 18Sep 21

Can you run it?

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

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
model.safetensors bf16 1.6 GB 2.4 GB ✅ Runs comfortably
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/sarashina2-2-0-5b-instruct-v0-1
{
  "hf_id": "sbintuitions/sarashina2.2-0.5b-instruct-v0.1",
  "params_b": 0.79,
  "context_length": 8192,
  "license": { "id": "mit", "commercial": "yes" },
  "downloads_30d": 247967,
  "vram_estimates": [
    { "quant": "bf16", "gb": 2.4 }
  ],
  "updated_at": "2026-09-11T01:00:41Z"
}
est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture
LlamaForCausalLM
Parameters
790 M
Tensor type
BF16
Context length
8,192
Vocabulary
102,400
Layers / heads
24 / 16
Licence
mit
First seen on the Hub
2025-02-26
Training datasets
undisclosed
Added to our catalog
2026-09-11
Compare with any text-generation model