llm-jp-4-33b-thinking-gguf
LLM-jp-4 is a series of large language models developed by the Research and Development Center for Large Language Models at the National Institute of Informatics.
Params
33.0 B
Context
—
Downloads 30d
271 K
Likes
11
Download history
daily snapshots · 32 days
▲ 63 K in the last 30 days (30.4%)
337 K225 K
Sep 25Oct 5Oct 15Oct 24
337 K192 K
Sep 23Oct 3Oct 14Oct 24
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 |
|---|---|---|---|---|
| llm-jp-4-33b-thinking-Q4_K_M.gguf | Q4_K_M | 20.2 GB | 27.6 GB | ❌ Won’t fit |
| llm-jp-4-33b-thinking-BF16.gguf | GGUF | 66.4 GB | 78.5 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$ ollama run llm-jp-4-33b-thinking-gguf # pin the quantization explicitly $ ollama run llm-jp-4-33b-thinking-gguf-q4_k_m
$ huggingface-cli download llm-jp/llm-jp-4-33b-thinking-gguf-GGUF \
llm-jp-4-33b-thinking-Q4_K_M.gguf --local-dir .
$ llama-cli -m llm-jp-4-33b-thinking-Q4_K_M.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/llm-jp-4-33b-thinking-gguf
{
"hf_id": "llm-jp/llm-jp-4-33b-thinking-gguf",
"params_b": 33.00,
"context_length": null,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 271493,
"vram_estimates": [
{ "quant": "GGUF", "gb": 78.5 },
{ "quant": "Q4_K_M", "gb": 27.6 }
],
"updated_at": "2026-10-08T01:00:11Z"
}
Specifications
- Parameters
- 33.0 B
- Licence
- apache-2.0
- First seen on the Hub
- 2026-08-18
- Training datasets
- undisclosed
- Added to our catalog
- 2026-09-23
Compare with any text-generation model