Model Intelligence Sheet
cybertruck32489/Jamba-Reasoning-3B-Agent-v1-gguf overview
Jamba Reasoning 3B Agent v1 gguf : GGUF This model was finetuned and converted to GGUF format using Unsloth https://github.com/unslothai/unsloth . Example usag…
Runs locally from ~668.0 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
5 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Jamba-Reasoning-3B-Agent-v1-F16.gguf | GGUF | F16 | 5.65 GB | Download |
| Jamba-Reasoning-3B-Agent-v1-Q4_K_M.gguf | GGUF | Q4_K_M | 1.71 GB | Download |
| Jamba-Reasoning-3B-Agent-v1-Q8_0.gguf | GGUF | Q8_0 | 3.01 GB | Download |
| LFM2.5-1.2B-Thinking-Fable5-hermes-opus-Agent.Q4_K_M.gguf | GGUF | GGUF | 697.0 MB | Download |
| LFM2.5-1.2B-Thinking-Fable5-hermes-opus-Agent.Q4_K_S.gguf | GGUF | GGUF | 668.0 MB | Download |
Model Details
| Model ID | cybertruck32489/Jamba-Reasoning-3B-Agent-v1-gguf |
|---|---|
| Author | cybertruck32489 |
| Pipeline | — |
| License | — |
| Base model | — |
| Last modified | 2026-07-21T13:45:17.000Z |
Model README
---
tags:
- gguf
- llama.cpp
- unsloth
---
Jamba-Reasoning-3B-Agent-v1-gguf : GGUF
This model was finetuned and converted to GGUF format using Unsloth.
Example usage:
- For text only LLMs:
llama-cli -hf cybertruck32489/Jamba-Reasoning-3B-Agent-v1-gguf --jinja - For multimodal models:
llama-mtmd-cli -hf cybertruck32489/Jamba-Reasoning-3B-Agent-v1-gguf --jinja
Available Model files:
LFM2.5-1.2B-Thinking-Fable5-hermes-opus-Agent.Q4_K_S.ggufLFM2.5-1.2B-Thinking-Fable5-hermes-opus-Agent.Q4_K_M.gguf
This was trained 2x faster with Unsloth
Run cybertruck32489/Jamba-Reasoning-3B-Agent-v1-gguf with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models