aaryank/iquest-coder-v1-40b-instruct-gguf Instruct.q4_1 GGUF - Free GGUF Download is indexed on GraySoft with repository links, GGUF quant files, and Hugging Face metadata. This page helps you pick a local model for guIDE or other runtimes. See related models in the same shard below.
Model Intelligence Sheet
aaryank/iquest-coder-v1-40b-instruct-gguf overview
!Logo
Downloads
379
Likes
7
Pipeline
text-generation
Library
gguf
Visibility
Public
Access
Open
Repository Files & Downloads
14 files detected
Direct downloads for all repository files
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| IQuest-Coder-V1-40B-Instruct.q2_k.gguf | GGUF | Q2_K | 13.76 GB | Download |
| IQuest-Coder-V1-40B-Instruct.q3_k_l.gguf | GGUF | Q3_K_L | 19.40 GB | Download |
| IQuest-Coder-V1-40B-Instruct.q3_k_m.gguf | GGUF | Q3_K_M | 17.92 GB | Download |
| IQuest-Coder-V1-40B-Instruct.q3_k_s.gguf | GGUF | Q3_K_S | 16.17 GB | Download |
| IQuest-Coder-V1-40B-Instruct.q4_0.gguf | GGUF | — | 20.95 GB | Download |
| IQuest-Coder-V1-40B-Instruct.q4_1.gguf | GGUF | — | 23.24 GB | Download |
| IQuest-Coder-V1-40B-Instruct.q4_k_m.gguf | GGUF | Q4_K_M | 22.38 GB | Download |
| IQuest-Coder-V1-40B-Instruct.q4_k_s.gguf | GGUF | Q4_K_S | 21.16 GB | Download |
| IQuest-Coder-V1-40B-Instruct.q5_0.gguf | GGUF | — | 25.53 GB | Download |
| IQuest-Coder-V1-40B-Instruct.q5_1.gguf | GGUF | — | 27.83 GB | Download |
| IQuest-Coder-V1-40B-Instruct.q5_k_m.gguf | GGUF | Q5_K_M | 26.26 GB | Download |
| IQuest-Coder-V1-40B-Instruct.q5_k_s.gguf | GGUF | Q5_K_S | 25.53 GB | Download |
| IQuest-Coder-V1-40B-Instruct.q6_k.gguf | GGUF | Q6_K | 30.41 GB | Download |
| IQuest-Coder-V1-40B-Instruct.q8_0.gguf | GGUF | — | 39.38 GB | Download |
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"base_model": "IQuestLab/IQuest-Coder-V1-40B-Instruct",
"base_model_relation": "quantized",
"language": [
"en"
],
"library_name": "gguf",
"license": "other",
"license_name": "iquestcoder",
"license_link": "https://huggingface.co/IQuestLab/IQuest-Coder-V1-40B-Instruct/blob/main/LICENSE",
"pipeline_tag": "text-generation",
"tags": [
"text-generation-inference",
"code",
"agent",
"swe-bench",
"gguf"
],
"frontmatter": {
"base_model": "IQuestLab/IQuest-Coder-V1-40B-Instruct",
"base_model_relation": "quantized",
"language": [
"en"
],
"library_name": "gguf",
"license": "other",
"license_name": "iquestcoder",
"license_link": "https://huggingface.co/IQuestLab/IQuest-Coder-V1-40B-Instruct/blob/main/LICENSE",
"pipeline_tag": "text-generation",
"tags": [
"text-generation-inference",
"code",
"agent",
"swe-bench",
"gguf"
]
},
"hero_image_url": "https://huggingface.co/IQuestLab/IQuest-Coder-V1-40B-Instruct/resolve/main/papers/iquest-coder-v1-logo.png",
"summary": "!Logo",
"quick_links": [],
"benchmark_table_html": "",
"readme_markdown": "---\nbase_model: IQuestLab/IQuest-Coder-V1-40B-Instruct\nbase_model_relation: quantized\nlanguage:\n - en\nlibrary_name: gguf\nlicense: other\nlicense_name: iquestcoder\nlicense_link: https://huggingface.co/IQuestLab/IQuest-Coder-V1-40B-Instruct/blob/main/LICENSE\npipeline_tag: text-generation\ntags:\n - text-generation-inference\n - code\n - agent\n - swe-bench\n - gguf\n---\n\n# IQuest-Coder-V1-40B-Instruct-GGUF\n\n\n\n## Description\n\nThis repository contains **GGUF** format model files for [IQuestLab's IQuest-Coder-V1-40B-Instruct](https://huggingface.co/IQuestLab/IQuest-Coder-V1-40B-Instruct).\n\n**IQuest-Coder-V1** is a state-of-the-art coding model built on a \"code-flow\" training paradigm. It captures the dynamic evolution of software logic, delivering exceptional performance on benchmarks like SWE-Bench Verified (81.4%) and BigCodeBench. This model natively supports a **128K context window**.\n\n## Evaluation Results\n\n\n\n## Files & Quantization\n\nTo see the available files, please verify the **Files and versions** tab.\n\n## How to Run (llama.cpp)\n\n**Recommended Parameters:**\nFor coding tasks, a lower temperature is generally recommended for precision.\n* **Temperature:** `0.2` (for code generation) or `0.7` (for creative explanations)\n* **Context:** `-c` (Adjust based on your VRAM/RAM. The model supports up to 128k).\n\n### CLI Example\n\n```bash\n./llama-cli -m IQuest-Coder-V1-40B-Instruct.Q4_K_M.gguf \\\n -c 8192 \\\n --temp 0.2 \\\n -p \"User: Write a Python function to calculate the Fibonacci sequence using dynamic programming.\\nAssistant:\" \\\n -cnv\n```\n\n### Server Example\n\n```bash\n./llama-server -m IQuest-Coder-V1-40B-Instruct.Q4_K_M.gguf \\\n --port 8080 \\\n --host 0.0.0.0 \\\n -c 16384 \\\n -ngl 99\n```",
"related_quantizations": []
},
"tags": [
"gguf",
"text-generation-inference",
"code",
"agent",
"swe-bench",
"text-generation",
"en",
"base_model:IQuestLab/IQuest-Coder-V1-40B-Instruct",
"base_model:quantized:IQuestLab/IQuest-Coder-V1-40B-Instruct",
"license:other",
"endpoints_compatible",
"region:us",
"conversational"
],
"likes": 7,
"downloads": 379,
"gated": false,
"private": false,
"last_modified": "2026-01-01T22:53:09.000Z",
"created_at": "2026-01-01T21:07:11.000Z",
"pipeline_tag": "text-generation",
"library_name": "gguf"
}
Source payload excerpt (from Hugging Face API)
{
"_id": "6956e1ff6b789d8bc24b67bd",
"id": "AaryanK/IQuest-Coder-V1-40B-Instruct-GGUF",
"modelId": "AaryanK/IQuest-Coder-V1-40B-Instruct-GGUF",
"sha": "b60fb684762bbcf202183564652535f0b4ceda0e",
"createdAt": "2026-01-01T21:07:11.000Z",
"lastModified": "2026-01-01T22:53:09.000Z",
"author": "AaryanK",
"downloads": 379,
"likes": 7,
"gated": false,
"private": false,
"pipeline_tag": "text-generation",
"library_name": "gguf",
"siblings_count": 16
}