POCKET-26B-GGUF
Meet POCKET-27B. Qwen3.8-27B in ARCHsloth Q6K GGUF. Choose files & download · Quality & limits
Params
26.0 B
Context
—
Downloads 30d
234 K
Likes
62
Download history
daily snapshots · 78 days
▲ 12 K in the last 30 days (4.7%)
250 K230 K
Oct 12Oct 22Nov 1Nov 10
366 K186 K
Aug 25Sep 20Oct 16Nov 10
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 |
|---|---|---|---|---|
| POCKET-26B-Q2_K.gguf | Q2_K | 11.1 GB | 16.6 GB | ✅ Runs comfortably |
| POCKET-26B-Q4_K_M.gguf | Q4_K_M | 16.8 GB | 22.9 GB | ⚠️ Tight — reduce context |
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 pocket-26b-gguf # pin the quantization explicitly $ ollama run pocket-26b-gguf-q4_k_m
$ huggingface-cli download FINAL-Bench/POCKET-26B-GGUF-GGUF \
POCKET-26B-Q4_K_M.gguf --local-dir .
$ llama-cli -m POCKET-26B-Q4_K_M.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/pocket-26b-gguf
{
"hf_id": "FINAL-Bench/POCKET-26B-GGUF",
"params_b": 26.00,
"context_length": null,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 234467,
"vram_estimates": [
{ "quant": "Q2_K", "gb": 16.6 },
{ "quant": "Q4_K_M", "gb": 22.9 }
],
"updated_at": "2026-11-10T01:00:34Z"
}
Specifications
- Parameters
- 26.0 B
- Licence
- apache-2.0
- First seen on the Hub
- 2026-07-24
- Base model
- gemma-4-26B-A4B-it
- Training datasets
- undisclosed
- Added to our catalog
- 2026-08-25
Family
Base model and the most-downloaded derivatives in the catalog.
Compare with any text-generation model