GraySoft
Download guIDE →
Model Comparison

m4-ai/tinymistral-248m-v2-instruct-ggufvstvall43/qwen3.5-14b-a3b-claude-4.6-opus-reasoning-distilled-reap-gguf

Side-by-side comparison of m4-ai/tinymistral-248m-v2-instruct-gguf and tvall43/qwen3.5-14b-a3b-claude-4.6-opus-reasoning-distilled-reap-gguf: downloads, license, context length, tasks, and benchmarks.

m4-ai/tinymistral-248m-v2-instruct-gguf

M4-ai · —

GGUF version of Locutusque/TinyMistral-248M-v2-Instruct. # Recommended inference parameters `` do_sample: true temperature: 0.1 top_p: 0.14 top_k: 12 repetition_penalty: 1.1 ` # Recommended prompt template ` user\n{user message}\nassistant\n{assistant message} ``

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

m4-ai/tinymistral-248m-v2-instruct-gguftvall43/qwen3.5-14b-a3b-claude-4.6-opus-reasoning-distilled-reap-gguf
AuthorM4-aitvall43
Pipeline Task—text-generation
Library—transformers
Downloads29,48220,490
Likes618
LicenseUnknownUnknown
Context Length——
Created2024-02-032026-03-09
Last Modified2024-02-032026-03-09
Tags
ggufendataset:HuggingFaceH4/ultrachat_200kbase_model:Locutusque/TinyMistral-248M-v2-Instructbase_model:quantized:Locutusque/TinyMistral-248M-v2-Instructlicense:apache-2.0endpoints_compatibleregion:us
transformersgguftext-generation-inferenceunslothqwen3_5_moeqwenqwen3.5reasoningchain-of-thoughttext-generation

View full details: m4-ai/tinymistral-248m-v2-instruct-gguf · tvall43/qwen3.5-14b-a3b-claude-4.6-opus-reasoning-distilled-reap-gguf