{"kind":"answer-pack","schemaVersion":"hugging-bay.answer-pack.v1","generatedAt":"2026-11-13T20:51:05.184Z","slug":"coding-model-8gb-gpu","title":"What coding model should I check for an 8 GB GPU?","question":"What coding model should I check for an 8 GB GPU?","description":"For this task and memory budget, Hugging Bay’s find-runnable pick is unsloth/Qwen2.5-Coder-3B-Instruct-GGUF (1.93 GB · Qwen2.5-Coder-3B-Instruct-Q4_K_M.gguf · Q4_K_M · SHA-256 32f00144…8c57c5b4). Memory fit is an estimate from recorded file size, not a runtime test on your machine. Read the license on the model page before downloading.","answerLead":"For this task and memory budget, Hugging Bay’s find-runnable pick is unsloth/Qwen2.5-Coder-3B-Instruct-GGUF (1.93 GB · Qwen2.5-Coder-3B-Instruct-Q4_K_M.gguf · Q4_K_M · SHA-256 32f00144…8c57c5b4). Memory fit is an estimate from recorded file size, not a runtime test on your machine. Read the license on the model page before downloading.","shortAnswer":"For this task and memory budget, Hugging Bay’s find-runnable pick is unsloth/Qwen2.5-Coder-3B-Instruct-GGUF (1.93 GB · Qwen2.5-Coder-3B-Instruct-Q4_K_M.gguf · Q4_K_M · SHA-256 32f00144…8c57c5b4). Memory fit is an estimate from recorded file size, not a runtime test on your machine. Read the license on the model page before downloading.","recommendation":{"artifactId":"hf-model-unsloth-qwen2-5-coder-3b-instruct-gguf","repo":"unsloth/Qwen2.5-Coder-3B-Instruct-GGUF","type":"llm","task":"text-generation","ranking":{"upstreamDownloads":0,"ladder":"qwen2.5-coder-3b"},"license":{"declared":"apache-2.0","label":"apache-2.0"},"memory":{"verdict":"comfortable","capacityFit":"comfortable","basis":"hosted-file-size","fitTier":"likely-fits","recommendedFile":{"path":"Qwen2.5-Coder-3B-Instruct-Q4_K_M.gguf","sizeBytes":1929902496,"sizeGb":1.93,"sha256":"32f0014400ca1c1f81e7fb5befa9b9af476ba967dcbf92bad27409228c57c5b4","readiness":"ready","downloadReady":true,"readinessCheckedAt":"2026-11-13T20:48:24.982Z","downloadUrl":"https://huggingbay.xyz/api/downloads/hf-model-unsloth-qwen2-5-coder-3b-instruct-gguf/Qwen2.5-Coder-3B-Instruct-Q4_K_M.gguf","serve_verdict":{"can_download":true,"bytes_verified":true,"signature":"signed","freshness":"current","checked_at":"2026-11-13T20:48:24.982Z","evidence_url":"/api/manifests/hf-model-unsloth-qwen2-5-coder-3b-instruct-gguf"},"signature_state":"signed"},"weightGb":1.929902496,"requestedMemoryGb":8},"hosting":{"selectedFilePath":"Qwen2.5-Coder-3B-Instruct-Q4_K_M.gguf","selectedFileHosted":true,"downloadReady":true,"runReady":false,"commandsAvailable":false,"completeRunnable":null},"downloadable":true,"downloadReady":true,"readiness":"ready","readinessCheckedAt":"2026-11-13T20:48:24.982Z","runEvidence":{"commandsAvailable":false,"deploymentPlanUrl":"https://huggingbay.xyz/api/v1/artifacts/hf-model-unsloth-qwen2-5-coder-3b-instruct-gguf/download-plan"},"why":"Tug's default for 8 GB machines. Q4_K_M keeps quality close to full size. 1.9 GB file leaves about 6 GB of VRAM.","runTested":false,"commandsAvailable":false,"runReady":false,"completeRunnable":null,"runReadyReasonCodes":["run-not-tested"],"serve_verdict":{"can_download":true,"bytes_verified":false,"signature":"unsigned","freshness":"current","checked_at":"2026-11-13T20:48:24.982Z","evidence_url":"/api/manifests/hf-model-unsloth-qwen2-5-coder-3b-instruct-gguf"}},"recommendationSource":"/api/agents/find-runnable","recommendationInput":{"task":"coding","ramGb":8,"hardware":"rtx4060-8"},"sourceApiUrl":"https://huggingbay.xyz/api/agents/find-runnable?task=coding&hardware=rtx4060-8","canonicalUrl":"https://huggingbay.xyz/answers/coding-model-8gb-gpu","webUrl":"https://huggingbay.xyz/answers/coding-model-8gb-gpu","apiUrl":"https://huggingbay.xyz/api/answers/coding-model-8gb-gpu","nextStep":{"label":"Check the current recommendation","href":"/api/agents/find-runnable?task=coding&hardware=rtx4060-8"},"rows":[{"artifactId":"hf-model-unsloth-qwen2-5-coder-3b-instruct-gguf","repo":"unsloth/Qwen2.5-Coder-3B-Instruct-GGUF","filename":"Qwen2.5-Coder-3B-Instruct-Q4_K_M.gguf","sizeBytes":1929902496,"quant":"Q4_K_M","sha256":"32f0014400ca1c1f81e7fb5befa9b9af476ba967dcbf92bad27409228c57c5b4","downloadUrl":"https://huggingbay.xyz/api/downloads/hf-model-unsloth-qwen2-5-coder-3b-instruct-gguf/Qwen2.5-Coder-3B-Instruct-Q4_K_M.gguf","readiness":"unknown","downloadReady":null,"readinessCheckedAt":null,"licenseLabel":"apache-2.0","rank":1,"fitLabel":null,"id":"hf-model-unsloth-qwen2-5-coder-3b-instruct-gguf","filePath":"Qwen2.5-Coder-3B-Instruct-Q4_K_M.gguf","type":"llm","license":"apache-2.0","citationUrl":"https://huggingbay.xyz/artifact/hf-model-unsloth-qwen2-5-coder-3b-instruct-gguf","apiUrl":"https://huggingbay.xyz/api/v1/artifacts/hf-model-unsloth-qwen2-5-coder-3b-instruct-gguf","cardMarkdownUrl":"https://huggingbay.xyz/api/artifacts/hf-model-unsloth-qwen2-5-coder-3b-instruct-gguf/card.md","reason":"For this task and memory budget, Hugging Bay’s find-runnable pick is unsloth/Qwen2.5-Coder-3B-Instruct-GGUF (1.93 GB · Qwen2.5-Coder-3B-Instruct-Q4_K_M.gguf · Q4_K_M · SHA-256 32f00144…8c57c5b4). Memory fit is an estimate from recorded file size, not a runtime test on your machine. Read the license on the model page before downloading.","hostingStatus":"hosted","hostedFiles":1,"serve_verdict":{"can_download":false,"bytes_verified":true,"signature":"signed","freshness":"stale","checked_at":null,"evidence_url":"/api/manifests/hf-model-unsloth-qwen2-5-coder-3b-instruct-gguf"},"signature_state":"signed"},{"artifactId":"hf-model-unsloth-qwen2-5-coder-1-5b-instruct-gguf","repo":"unsloth/Qwen2.5-Coder-1.5B-Instruct-GGUF","filename":"Qwen2.5-Coder-1.5B-Instruct-Q4_K_M.gguf","sizeBytes":986048032,"quant":"Q4_K_M","sha256":"5ecd6f45e137154099741291848db7415b5effa1ae69228f20dacea31dbf5ce4","downloadUrl":"https://huggingbay.xyz/api/downloads/hf-model-unsloth-qwen2-5-coder-1-5b-instruct-gguf/Qwen2.5-Coder-1.5B-Instruct-Q4_K_M.gguf","readiness":"unknown","downloadReady":null,"readinessCheckedAt":null,"licenseLabel":"apache-2.0","rank":2,"fitLabel":null,"id":"hf-model-unsloth-qwen2-5-coder-1-5b-instruct-gguf","filePath":"Qwen2.5-Coder-1.5B-Instruct-Q4_K_M.gguf","type":"llm","license":"apache-2.0","citationUrl":"https://huggingbay.xyz/artifact/hf-model-unsloth-qwen2-5-coder-1-5b-instruct-gguf","apiUrl":"https://huggingbay.xyz/api/v1/artifacts/hf-model-unsloth-qwen2-5-coder-1-5b-instruct-gguf","cardMarkdownUrl":"https://huggingbay.xyz/api/artifacts/hf-model-unsloth-qwen2-5-coder-1-5b-instruct-gguf/card.md","reason":"For this task and memory budget, Hugging Bay’s find-runnable pick is unsloth/Qwen2.5-Coder-3B-Instruct-GGUF (1.93 GB · Qwen2.5-Coder-3B-Instruct-Q4_K_M.gguf · Q4_K_M · SHA-256 32f00144…8c57c5b4). Memory fit is an estimate from recorded file size, not a runtime test on your machine. Read the license on the model page before downloading.","hostingStatus":"hosted","hostedFiles":1,"serve_verdict":{"can_download":false,"bytes_verified":true,"signature":"unsigned","freshness":"stale","checked_at":null,"evidence_url":"/api/manifests/hf-model-unsloth-qwen2-5-coder-1-5b-instruct-gguf"},"signature_state":"unsigned"},{"artifactId":"hf-model-qwen-qwen2-5-coder-7b-instruct-gguf","repo":"Qwen/Qwen2.5-Coder-7B-Instruct-GGUF","filename":"qwen2.5-coder-7b-instruct-q3_k_m.gguf","sizeBytes":3808391104,"quant":"Q3_K_M","sha256":"ff5c64615cf8a44651d208e9d8da1f753feefc21605e6c1ee67957aa77257c3c","downloadUrl":"https://huggingbay.xyz/api/downloads/hf-model-qwen-qwen2-5-coder-7b-instruct-gguf/qwen2.5-coder-7b-instruct-q3_k_m.gguf","readiness":"unknown","downloadReady":null,"readinessCheckedAt":null,"licenseLabel":"No license stated","rank":3,"fitLabel":null,"id":"hf-model-qwen-qwen2-5-coder-7b-instruct-gguf","filePath":"qwen2.5-coder-7b-instruct-q3_k_m.gguf","type":"llm","license":"No license stated","citationUrl":"https://huggingbay.xyz/artifact/hf-model-qwen-qwen2-5-coder-7b-instruct-gguf","apiUrl":"https://huggingbay.xyz/api/v1/artifacts/hf-model-qwen-qwen2-5-coder-7b-instruct-gguf","cardMarkdownUrl":"https://huggingbay.xyz/api/artifacts/hf-model-qwen-qwen2-5-coder-7b-instruct-gguf/card.md","reason":"For this task and memory budget, Hugging Bay’s find-runnable pick is unsloth/Qwen2.5-Coder-3B-Instruct-GGUF (1.93 GB · Qwen2.5-Coder-3B-Instruct-Q4_K_M.gguf · Q4_K_M · SHA-256 32f00144…8c57c5b4). Memory fit is an estimate from recorded file size, not a runtime test on your machine. Read the license on the model page before downloading.","hostingStatus":"hosted","hostedFiles":1,"serve_verdict":{"can_download":false,"bytes_verified":true,"signature":"signed","freshness":"stale","checked_at":null,"evidence_url":"/api/manifests/hf-model-qwen-qwen2-5-coder-7b-instruct-gguf"},"signature_state":"signed"}],"citationTargets":["https://huggingbay.xyz/artifact/hf-model-unsloth-qwen2-5-coder-3b-instruct-gguf","https://huggingbay.xyz/artifact/hf-model-unsloth-qwen2-5-coder-1-5b-instruct-gguf","https://huggingbay.xyz/artifact/hf-model-qwen-qwen2-5-coder-7b-instruct-gguf"],"extractionApis":["https://huggingbay.xyz/api/v1/artifacts/hf-model-unsloth-qwen2-5-coder-3b-instruct-gguf","https://huggingbay.xyz/api/v1/artifacts/hf-model-unsloth-qwen2-5-coder-1-5b-instruct-gguf","https://huggingbay.xyz/api/v1/artifacts/hf-model-qwen-qwen2-5-coder-7b-instruct-gguf"],"guidance":[],"note":{"summary":"Downloadable doesn't mean tested: this record says whether the exact file can be downloaded now, not that the model is complete or that it runs."}}