tvall43/qwen3.5-14b-a3b-claude-4.6-opus-reasoning-distilled-reap-ggufvsvaluefx9507/tifa-deepsexv2-7b-mgrpo-gguf-q8
Side-by-side comparison of tvall43/qwen3.5-14b-a3b-claude-4.6-opus-reasoning-distilled-reap-gguf and valuefx9507/tifa-deepsexv2-7b-mgrpo-gguf-q8: downloads, license, context length, tasks, and benchmarks.
tvall43/qwen3.5-14b-a3b-claude-4.6-opus-reasoning-distilled-reap-gguf
can i fit moe qwen3.5 in 10gb vram? since thats already risky, lets yolo and use claude distil too. 0.65 compression this time. my original goal was 8gb vram but i mathed wrong somewhere. that fits fine on my gpro x080 but not single gpu in the radeon v340l. maybe ill give it an…
valuefx9507/tifa-deepsexv2-7b-mgrpo-gguf-q8
prompt = """你是一个小女孩/你是一个XX角色... 我走进门，看到你冲上来迎接我 需要体现人物的气质 加入环境描写 保持对话风格 我看到XX进门...""" `` **参数推荐**： `python generation_config = { "temperature": 0.75, "top_p": 0.6, "repetition_penalty": 1.08, "max_new_tokens": 1536, "do_sample": True } ``
Side-by-side Specifications
| tvall43/qwen3.5-14b-a3b-claude-4.6-opus-reasoning-distilled-reap-gguf | valuefx9507/tifa-deepsexv2-7b-mgrpo-gguf-q8 | |
|---|---|---|
| Author | tvall43 | ValueFX9507 |
| Pipeline Task | text-generation | reinforcement-learning |
| Library | transformers | transformers |
| Downloads | 20,490 | 23,629 |
| Likes | 18 | 201 |
| License | Unknown | Unknown |
| Context Length | — | — |
| Created | 2026-03-09 | 2025-02-15 |
| Last Modified | 2026-03-09 | 2025-03-28 |
| Tags |
View full details: tvall43/qwen3.5-14b-a3b-claude-4.6-opus-reasoning-distilled-reap-gguf · valuefx9507/tifa-deepsexv2-7b-mgrpo-gguf-q8