Parable-Qwen3-8B-Claude-Fable-5-GGUF
> ~6 GB of RAM is all you need. Laptop, mid-range GPU, yesterday's desktop — the Q4 build runs > anywhere with that much headroom. One command and you have a private, offline reasoning model on your machine: > > bash > ollama run hf.co/AnkitAI/Parable-Qwen3-8B-Claude-Fable-5-GGUF:Q4KM >
Params
—
Context
—
Downloads 30d
593 K
Likes
4
Download history
daily snapshots · 37 days
▲ 333 K in the last 30 days (128.3%)
603 K273 K
Aug 22Sep 1Sep 11Sep 20
603 K181 K
Aug 15Aug 27Sep 8Sep 20
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 |
|---|---|---|---|---|
| Parable-Qwen3-8B-Claude-Fable-5-GGUF-Q4_K_M.gguf | Q4_K_M | 5.0 GB | 6.0 GB | ✅ Runs comfortably |
| Parable-Qwen3-8B-Claude-Fable-5-GGUF-Q5_K_M.gguf | Q5_K_M | 5.9 GB | 6.9 GB | ✅ Runs comfortably |
| Parable-Qwen3-8B-Claude-Fable-5-GGUF-Q6_K.gguf | Q6_K | 6.7 GB | 7.9 GB | ✅ Runs comfortably |
| Parable-Qwen3-8B-Claude-Fable-5-GGUF-Q8_0.gguf | Q8_0 | 8.7 GB | 10.1 GB | ✅ Runs comfortably |
| Parable-Qwen3-8B-Claude-Fable-5-GGUF-F16.gguf | GGUF | 16.4 GB | 18.5 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$ ollama run parable-qwen3-8b-claude-fable-5-gguf # pin the quantization explicitly $ ollama run parable-qwen3-8b-claude-fable-5-gguf-q4_k_m
$ huggingface-cli download AnkitAI/Parable-Qwen3-8B-Claude-Fable-5-GGUF-GGUF \
Parable-Qwen3-8B-Claude-Fable-5-GGUF-Q4_K_M.gguf --local-dir .
$ llama-cli -m Parable-Qwen3-8B-Claude-Fable-5-GGUF-Q4_K_M.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/parable-qwen3-8b-claude-fable-5-gguf
{
"hf_id": "AnkitAI/Parable-Qwen3-8B-Claude-Fable-5-GGUF",
"params_b": null,
"context_length": null,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 593293,
"vram_estimates": [
{ "quant": "GGUF", "gb": 18.5 },
{ "quant": "Q4_K_M", "gb": 6.0 }
],
"updated_at": "2026-08-21T01:00:25Z"
}
Specifications
- Licence
- apache-2.0
- First seen on the Hub
- 2026-07-14
- Base model
- Qwen3-8B
- Training datasets
- Glint-Research/Fable-5-traces, Roman1111111/gpt5.5-terminal
- Added to our catalog
- 2026-08-15
Compare with any text-generation model