GraySoft
Download guIDE →
Model Comparison

ccssne/gemma-4-31b-it-heretic-ara-ggufvstvall43/qwen3.5-14b-a3b-claude-4.6-opus-reasoning-distilled-reap-gguf

Side-by-side comparison of ccssne/gemma-4-31b-it-heretic-ara-gguf and tvall43/qwen3.5-14b-a3b-claude-4.6-opus-reasoning-distilled-reap-gguf: downloads, license, context length, tasks, and benchmarks.

ccssne/gemma-4-31b-it-heretic-ara-gguf

CCSSNE · —

# Gemma-4-31B-It-Heretic-GGUF Quantized using Unsloth on RTX 4070 Laptop . This version includes the vision adapter (mmproj) and is optimized for local inference.

tvall43/qwen3.5-14b-a3b-claude-4.6-opus-reasoning-distilled-reap-gguf

tvall43 · text-generation

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…

Side-by-side Specifications

ccssne/gemma-4-31b-it-heretic-ara-gguftvall43/qwen3.5-14b-a3b-claude-4.6-opus-reasoning-distilled-reap-gguf
AuthorCCSSNEtvall43
Pipeline Task—text-generation
Librarygguftransformers
Downloads48,71420,490
Likes418
LicenseUnknownUnknown
Context Length——
Created2026-04-032026-03-09
Last Modified2026-04-032026-03-09
Tags
ggufunslothgemma-4quantizedbase_model:trohrbaugh/gemma-4-31b-it-heretic-arabase_model:quantized:trohrbaugh/gemma-4-31b-it-heretic-araendpoints_compatibleregion:usconversational
transformersgguftext-generation-inferenceunslothqwen3_5_moeqwenqwen3.5reasoningchain-of-thoughttext-generation

View full details: ccssne/gemma-4-31b-it-heretic-ara-gguf · tvall43/qwen3.5-14b-a3b-claude-4.6-opus-reasoning-distilled-reap-gguf