Nanbeige_Nanbeige4.3-33B-GGUF
Model details: - Parameter count: 33B (source checkpoint) - Input support: text - Speculative decoding: no - imatrix: yes - details
Params
33.0 B
Context
—
Downloads 30d
140 K
Likes
31
Download history
tracking started — chart appears after 7 days of snapshots (2 recorded)140 K downloads in the last 30 days
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 |
|---|---|---|---|---|
| Nanbeige_Nanbeige4.3-33B-IQ2_XXS.gguf | IQ2_XXS | 10.1 GB | 16.5 GB | ✅ Runs comfortably |
| Nanbeige_Nanbeige4.3-33B-IQ2_XS.gguf | IQ2_XS | 10.6 GB | 17.1 GB | ✅ Runs comfortably |
| Nanbeige_Nanbeige4.3-33B-IQ2_S.gguf | IQ2_S | 11.2 GB | 17.7 GB | ✅ Runs comfortably |
| Nanbeige_Nanbeige4.3-33B-IQ2_M.gguf | IQ2_M | 12.2 GB | 18.9 GB | ✅ Runs comfortably |
| Nanbeige_Nanbeige4.3-33B-IQ3_XXS.gguf | IQ3_XXS | 14.5 GB | 21.4 GB | ⚠️ Tight — reduce context |
| Nanbeige_Nanbeige4.3-33B-IQ3_XS.gguf | IQ3_XS | 15.2 GB | 22.2 GB | ⚠️ Tight — reduce context |
| Nanbeige_Nanbeige4.3-33B-IQ3_M.gguf | IQ3_M | 17.8 GB | 25.0 GB | ❌ Won’t fit |
| Nanbeige_Nanbeige4.3-33B-IQ4_NL.gguf | IQ4_NL | 20.9 GB | 28.4 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$ ollama run nanbeige-nanbeige4-3-33b-gguf # pin the quantization explicitly $ ollama run nanbeige-nanbeige4-3-33b-gguf-iq2_m
$ huggingface-cli download bartowski/Nanbeige_Nanbeige4.3-33B-GGUF-GGUF \
Nanbeige_Nanbeige4.3-33B-IQ2_M.gguf --local-dir .
$ llama-cli -m Nanbeige_Nanbeige4.3-33B-IQ2_M.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/nanbeige-nanbeige4-3-33b-gguf
{
"hf_id": "bartowski/Nanbeige_Nanbeige4.3-33B-GGUF",
"params_b": 33.00,
"context_length": null,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 139628,
"vram_estimates": [
{ "quant": "IQ2_M", "gb": 18.9 },
{ "quant": "IQ2_S", "gb": 17.7 }
],
"updated_at": "2026-11-09T01:00:08Z"
}
Specifications
- Parameters
- 33.0 B
- Licence
- apache-2.0
- First seen on the Hub
- 2026-10-25
- Training datasets
- undisclosed
- Added to our catalog
- 2026-11-09
Compare with any text-generation model