b4ph/qwen3-4b-lowram-bench

zetlyn/models-gguf quantisation gguf b4ph/qwen3-4b-lowram-bench hf Qwen/Qwen3-4B known 2026-09-04

https://huggingface.co/b4ph/qwen3-4b-lowram-bench

Properties

authorb4ph
receipt
Source
GGUF quantisations
Its words
b4ph
Read by
field:author
Said since
2026-09-29 09:50 UTC
Last answered
2026-10-04 18:16 UTC
Original
open at the source
What the source handed over
{
  "_id": "6a9a1507d4e2ad4c43a8940b",
  "author": "b4ph",
  "cardData": {
    "base_model": "Qwen/Qwen3-4B",
    "base_model_relation": "quantized",
    "datasets": [
      "wikitext-2"
    ],
    "language": [
      "en"
    ],
    "library_name": "llama.cpp",
    "license": "apache-2.0",
    "pipeline_tag": "text-generation",
    "tags": [
      "llama.cpp",
      "gguf",
      "quantization",
      "qwen3",
      "benchmark",
      "low-ram-inference",
      "cpu-inference",
      "perplexity",
      "imatrix",
      "k-quants"
    ]
  },
  "createdAt": "2026-09-04T00:47:03.000Z",
  "downloads": 763,
  "gated": false,
  "id": "b4ph/qwen3-4b-lowram-bench",
  "lastModified": "2026-09-07T17:42:05.000Z",
  "library_name": "llama.cpp",
  "likes": 3,
  "modelId": "b4ph/qwen3-4b-lowram-bench",
  "pipeline_tag": "text-generation",
  "private": false,
  "sha": "89eba2cb2e5245fb62ab42ac3cda242dd1daca35",
  "siblings": [
    {
      "rfilename": ".gitattributes"
    },
    {
      "rfilename": "LICENSE"
    },
    {
      "rfilename": "Qwen3-4B-F16.gguf"
    },
    {
      "rfilename": "Qwen3-4B-Q3_K_M.gguf"
    },
    {
      "rfilename": "Qwen3-4B-Q3_K_M_imatrix.gguf"
    },
    {
      "rfilename": "Qwen3-4B-Q4_K_M.gguf"
    },
    {
      "rfilename": "Qwen3-4B-Q4_K_M_imatrix.gguf"
    },
    {
      "rfilename": "Qwen3-4B-Q5_K_M.gguf"
    },
    {
      "rfilename": "Qwen3-4B-Q6_K.gguf"
    },
    {
      "rfilename": "Qwen3-4B-Q8_0.gguf"
    },
    {
      "rfilename": "README.md"
    },
    {
      "rfilename": "assets/benchmarkhf-dark-mode-only.png"
    },
    {
      "rfilename": "assets/benchmarkhf-light-mode-only.png"
    },
    {
      "rfilename": "bench/bench_F16_v2.md"
    },
    {
      "rfilename": "bench/bench_Q3_K_M_imatrix_v2.md"
    },
    {
      "rfilename": "bench/bench_Q3_K_M_v2.md"
    },
    {
      "rfilename": "bench/bench_Q4_K_M_imatrix_v2.md"
    },
    {
      "rfilename": "bench/bench_Q4_K_M_v2.md"
    },
    {
      "rfilename": "bench/bench_Q5_K_M_v2.md"
    },
    {
      "rfilename": "bench/bench_Q6_K_v2.md"
    },
    {
      "rfilename": "bench/bench_Q8_0_v2.md"
    },
    {
      "rfilename": "bench/perp_F16.log"
    },
    {
      "rfilename": "bench/perp_Q3_K_M.log"
    },
    {
      "rfilename": "bench/perp_Q3_K_M_imatrix.log"
    },
    {
      "rfilename": "bench/perp_Q4_K_M.log"
    },
    {
      "rfilename": "bench/perp_Q4_K_M_imatrix.log"
    },
    {
      "rfilename": "bench/perp_Q5_K_M.log"
    },
    {
      "rfilename": "bench/perp_Q6_K.log"
    },
    {
      "rfilename": "bench/perp_Q8_0.log"
    },
    {
      "rfilename": "bench/run_bench.sh"
    },
    {
      "rfilename": "data/results.tsv"
    },
    {
      "rfilename": "data/wiki.test.raw"
    }
  ],
  "tags": [
    "llama.cpp",
    "gguf",
    "quantization",
    "qwen3",
    "benchmark",
    "low-ram-inference",
    "cpu-inference",
    "perplexity",
    "imatrix",
    "k-quants",
    "text-generation",
    "en",
    "dataset:wikitext-2",
    "base_model:Qwen/Qwen3-4B",
    "base_model:quantized:Qwen/Qwen3-4B",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ]
}
baseQwen/Qwen3-4B
receipt
Source
GGUF quantisations
Its words
Qwen/Qwen3-4B
Read by
field:cardData.base_model[]
Said since
2026-09-29 09:50 UTC
Last answered
2026-10-04 18:16 UTC
Original
open at the source
What the source handed over
{
  "_id": "6a9a1507d4e2ad4c43a8940b",
  "author": "b4ph",
  "cardData": {
    "base_model": "Qwen/Qwen3-4B",
    "base_model_relation": "quantized",
    "datasets": [
      "wikitext-2"
    ],
    "language": [
      "en"
    ],
    "library_name": "llama.cpp",
    "license": "apache-2.0",
    "pipeline_tag": "text-generation",
    "tags": [
      "llama.cpp",
      "gguf",
      "quantization",
      "qwen3",
      "benchmark",
      "low-ram-inference",
      "cpu-inference",
      "perplexity",
      "imatrix",
      "k-quants"
    ]
  },
  "createdAt": "2026-09-04T00:47:03.000Z",
  "downloads": 763,
  "gated": false,
  "id": "b4ph/qwen3-4b-lowram-bench",
  "lastModified": "2026-09-07T17:42:05.000Z",
  "library_name": "llama.cpp",
  "likes": 3,
  "modelId": "b4ph/qwen3-4b-lowram-bench",
  "pipeline_tag": "text-generation",
  "private": false,
  "sha": "89eba2cb2e5245fb62ab42ac3cda242dd1daca35",
  "siblings": [
    {
      "rfilename": ".gitattributes"
    },
    {
      "rfilename": "LICENSE"
    },
    {
      "rfilename": "Qwen3-4B-F16.gguf"
    },
    {
      "rfilename": "Qwen3-4B-Q3_K_M.gguf"
    },
    {
      "rfilename": "Qwen3-4B-Q3_K_M_imatrix.gguf"
    },
    {
      "rfilename": "Qwen3-4B-Q4_K_M.gguf"
    },
    {
      "rfilename": "Qwen3-4B-Q4_K_M_imatrix.gguf"
    },
    {
      "rfilename": "Qwen3-4B-Q5_K_M.gguf"
    },
    {
      "rfilename": "Qwen3-4B-Q6_K.gguf"
    },
    {
      "rfilename": "Qwen3-4B-Q8_0.gguf"
    },
    {
      "rfilename": "README.md"
    },
    {
      "rfilename": "assets/benchmarkhf-dark-mode-only.png"
    },
    {
      "rfilename": "assets/benchmarkhf-light-mode-only.png"
    },
    {
      "rfilename": "bench/bench_F16_v2.md"
    },
    {
      "rfilename": "bench/bench_Q3_K_M_imatrix_v2.md"
    },
    {
      "rfilename": "bench/bench_Q3_K_M_v2.md"
    },
    {
      "rfilename": "bench/bench_Q4_K_M_imatrix_v2.md"
    },
    {
      "rfilename": "bench/bench_Q4_K_M_v2.md"
    },
    {
      "rfilename": "bench/bench_Q5_K_M_v2.md"
    },
    {
      "rfilename": "bench/bench_Q6_K_v2.md"
    },
    {
      "rfilename": "bench/bench_Q8_0_v2.md"
    },
    {
      "rfilename": "bench/perp_F16.log"
    },
    {
      "rfilename": "bench/perp_Q3_K_M.log"
    },
    {
      "rfilename": "bench/perp_Q3_K_M_imatrix.log"
    },
    {
      "rfilename": "bench/perp_Q4_K_M.log"
    },
    {
      "rfilename": "bench/perp_Q4_K_M_imatrix.log"
    },
    {
      "rfilename": "bench/perp_Q5_K_M.log"
    },
    {
      "rfilename": "bench/perp_Q6_K.log"
    },
    {
      "rfilename": "bench/perp_Q8_0.log"
    },
    {
      "rfilename": "bench/run_bench.sh"
    },
    {
      "rfilename": "data/results.tsv"
    },
    {
      "rfilename": "data/wiki.test.raw"
    }
  ],
  "tags": [
    "llama.cpp",
    "gguf",
    "quantization",
    "qwen3",
    "benchmark",
    "low-ram-inference",
    "cpu-inference",
    "perplexity",
    "imatrix",
    "k-quants",
    "text-generation",
    "en",
    "dataset:wikitext-2",
    "base_model:Qwen/Qwen3-4B",
    "base_model:quantized:Qwen/Qwen3-4B",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ]
}
downloads763
receipt
Source
GGUF quantisations
Its words
763
Read by
field:downloads
Said since
2026-09-29 09:50 UTC
Last answered
2026-10-04 18:16 UTC
Original
open at the source
What the source handed over
{
  "_id": "6a9a1507d4e2ad4c43a8940b",
  "author": "b4ph",
  "cardData": {
    "base_model": "Qwen/Qwen3-4B",
    "base_model_relation": "quantized",
    "datasets": [
      "wikitext-2"
    ],
    "language": [
      "en"
    ],
    "library_name": "llama.cpp",
    "license": "apache-2.0",
    "pipeline_tag": "text-generation",
    "tags": [
      "llama.cpp",
      "gguf",
      "quantization",
      "qwen3",
      "benchmark",
      "low-ram-inference",
      "cpu-inference",
      "perplexity",
      "imatrix",
      "k-quants"
    ]
  },
  "createdAt": "2026-09-04T00:47:03.000Z",
  "downloads": 763,
  "gated": false,
  "id": "b4ph/qwen3-4b-lowram-bench",
  "lastModified": "2026-09-07T17:42:05.000Z",
  "library_name": "llama.cpp",
  "likes": 3,
  "modelId": "b4ph/qwen3-4b-lowram-bench",
  "pipeline_tag": "text-generation",
  "private": false,
  "sha": "89eba2cb2e5245fb62ab42ac3cda242dd1daca35",
  "siblings": [
    {
      "rfilename": ".gitattributes"
    },
    {
      "rfilename": "LICENSE"
    },
    {
      "rfilename": "Qwen3-4B-F16.gguf"
    },
    {
      "rfilename": "Qwen3-4B-Q3_K_M.gguf"
    },
    {
      "rfilename": "Qwen3-4B-Q3_K_M_imatrix.gguf"
    },
    {
      "rfilename": "Qwen3-4B-Q4_K_M.gguf"
    },
    {
      "rfilename": "Qwen3-4B-Q4_K_M_imatrix.gguf"
    },
    {
      "rfilename": "Qwen3-4B-Q5_K_M.gguf"
    },
    {
      "rfilename": "Qwen3-4B-Q6_K.gguf"
    },
    {
      "rfilename": "Qwen3-4B-Q8_0.gguf"
    },
    {
      "rfilename": "README.md"
    },
    {
      "rfilename": "assets/benchmarkhf-dark-mode-only.png"
    },
    {
      "rfilename": "assets/benchmarkhf-light-mode-only.png"
    },
    {
      "rfilename": "bench/bench_F16_v2.md"
    },
    {
      "rfilename": "bench/bench_Q3_K_M_imatrix_v2.md"
    },
    {
      "rfilename": "bench/bench_Q3_K_M_v2.md"
    },
    {
      "rfilename": "bench/bench_Q4_K_M_imatrix_v2.md"
    },
    {
      "rfilename": "bench/bench_Q4_K_M_v2.md"
    },
    {
      "rfilename": "bench/bench_Q5_K_M_v2.md"
    },
    {
      "rfilename": "bench/bench_Q6_K_v2.md"
    },
    {
      "rfilename": "bench/bench_Q8_0_v2.md"
    },
    {
      "rfilename": "bench/perp_F16.log"
    },
    {
      "rfilename": "bench/perp_Q3_K_M.log"
    },
    {
      "rfilename": "bench/perp_Q3_K_M_imatrix.log"
    },
    {
      "rfilename": "bench/perp_Q4_K_M.log"
    },
    {
      "rfilename": "bench/perp_Q4_K_M_imatrix.log"
    },
    {
      "rfilename": "bench/perp_Q5_K_M.log"
    },
    {
      "rfilename": "bench/perp_Q6_K.log"
    },
    {
      "rfilename": "bench/perp_Q8_0.log"
    },
    {
      "rfilename": "bench/run_bench.sh"
    },
    {
      "rfilename": "data/results.tsv"
    },
    {
      "rfilename": "data/wiki.test.raw"
    }
  ],
  "tags": [
    "llama.cpp",
    "gguf",
    "quantization",
    "qwen3",
    "benchmark",
    "low-ram-inference",
    "cpu-inference",
    "perplexity",
    "imatrix",
    "k-quants",
    "text-generation",
    "en",
    "dataset:wikitext-2",
    "base_model:Qwen/Qwen3-4B",
    "base_model:quantized:Qwen/Qwen3-4B",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ]
}
licenceapache-2.0
receipt
Source
GGUF quantisations
Its words
apache-2.0
Read by
field:cardData.license
Said since
2026-09-29 09:50 UTC
Last answered
2026-10-04 18:16 UTC
Original
open at the source
What the source handed over
{
  "_id": "6a9a1507d4e2ad4c43a8940b",
  "author": "b4ph",
  "cardData": {
    "base_model": "Qwen/Qwen3-4B",
    "base_model_relation": "quantized",
    "datasets": [
      "wikitext-2"
    ],
    "language": [
      "en"
    ],
    "library_name": "llama.cpp",
    "license": "apache-2.0",
    "pipeline_tag": "text-generation",
    "tags": [
      "llama.cpp",
      "gguf",
      "quantization",
      "qwen3",
      "benchmark",
      "low-ram-inference",
      "cpu-inference",
      "perplexity",
      "imatrix",
      "k-quants"
    ]
  },
  "createdAt": "2026-09-04T00:47:03.000Z",
  "downloads": 763,
  "gated": false,
  "id": "b4ph/qwen3-4b-lowram-bench",
  "lastModified": "2026-09-07T17:42:05.000Z",
  "library_name": "llama.cpp",
  "likes": 3,
  "modelId": "b4ph/qwen3-4b-lowram-bench",
  "pipeline_tag": "text-generation",
  "private": false,
  "sha": "89eba2cb2e5245fb62ab42ac3cda242dd1daca35",
  "siblings": [
    {
      "rfilename": ".gitattributes"
    },
    {
      "rfilename": "LICENSE"
    },
    {
      "rfilename": "Qwen3-4B-F16.gguf"
    },
    {
      "rfilename": "Qwen3-4B-Q3_K_M.gguf"
    },
    {
      "rfilename": "Qwen3-4B-Q3_K_M_imatrix.gguf"
    },
    {
      "rfilename": "Qwen3-4B-Q4_K_M.gguf"
    },
    {
      "rfilename": "Qwen3-4B-Q4_K_M_imatrix.gguf"
    },
    {
      "rfilename": "Qwen3-4B-Q5_K_M.gguf"
    },
    {
      "rfilename": "Qwen3-4B-Q6_K.gguf"
    },
    {
      "rfilename": "Qwen3-4B-Q8_0.gguf"
    },
    {
      "rfilename": "README.md"
    },
    {
      "rfilename": "assets/benchmarkhf-dark-mode-only.png"
    },
    {
      "rfilename": "assets/benchmarkhf-light-mode-only.png"
    },
    {
      "rfilename": "bench/bench_F16_v2.md"
    },
    {
      "rfilename": "bench/bench_Q3_K_M_imatrix_v2.md"
    },
    {
      "rfilename": "bench/bench_Q3_K_M_v2.md"
    },
    {
      "rfilename": "bench/bench_Q4_K_M_imatrix_v2.md"
    },
    {
      "rfilename": "bench/bench_Q4_K_M_v2.md"
    },
    {
      "rfilename": "bench/bench_Q5_K_M_v2.md"
    },
    {
      "rfilename": "bench/bench_Q6_K_v2.md"
    },
    {
      "rfilename": "bench/bench_Q8_0_v2.md"
    },
    {
      "rfilename": "bench/perp_F16.log"
    },
    {
      "rfilename": "bench/perp_Q3_K_M.log"
    },
    {
      "rfilename": "bench/perp_Q3_K_M_imatrix.log"
    },
    {
      "rfilename": "bench/perp_Q4_K_M.log"
    },
    {
      "rfilename": "bench/perp_Q4_K_M_imatrix.log"
    },
    {
      "rfilename": "bench/perp_Q5_K_M.log"
    },
    {
      "rfilename": "bench/perp_Q6_K.log"
    },
    {
      "rfilename": "bench/perp_Q8_0.log"
    },
    {
      "rfilename": "bench/run_bench.sh"
    },
    {
      "rfilename": "data/results.tsv"
    },
    {
      "rfilename": "data/wiki.test.raw"
    }
  ],
  "tags": [
    "llama.cpp",
    "gguf",
    "quantization",
    "qwen3",
    "benchmark",
    "low-ram-inference",
    "cpu-inference",
    "perplexity",
    "imatrix",
    "k-quants",
    "text-generation",
    "en",
    "dataset:wikitext-2",
    "base_model:Qwen/Qwen3-4B",
    "base_model:quantized:Qwen/Qwen3-4B",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ]
}
likes3
receipt
Source
GGUF quantisations
Its words
3
Read by
field:likes
Said since
2026-09-29 09:50 UTC
Last answered
2026-10-04 18:16 UTC
Original
open at the source
What the source handed over
{
  "_id": "6a9a1507d4e2ad4c43a8940b",
  "author": "b4ph",
  "cardData": {
    "base_model": "Qwen/Qwen3-4B",
    "base_model_relation": "quantized",
    "datasets": [
      "wikitext-2"
    ],
    "language": [
      "en"
    ],
    "library_name": "llama.cpp",
    "license": "apache-2.0",
    "pipeline_tag": "text-generation",
    "tags": [
      "llama.cpp",
      "gguf",
      "quantization",
      "qwen3",
      "benchmark",
      "low-ram-inference",
      "cpu-inference",
      "perplexity",
      "imatrix",
      "k-quants"
    ]
  },
  "createdAt": "2026-09-04T00:47:03.000Z",
  "downloads": 763,
  "gated": false,
  "id": "b4ph/qwen3-4b-lowram-bench",
  "lastModified": "2026-09-07T17:42:05.000Z",
  "library_name": "llama.cpp",
  "likes": 3,
  "modelId": "b4ph/qwen3-4b-lowram-bench",
  "pipeline_tag": "text-generation",
  "private": false,
  "sha": "89eba2cb2e5245fb62ab42ac3cda242dd1daca35",
  "siblings": [
    {
      "rfilename": ".gitattributes"
    },
    {
      "rfilename": "LICENSE"
    },
    {
      "rfilename": "Qwen3-4B-F16.gguf"
    },
    {
      "rfilename": "Qwen3-4B-Q3_K_M.gguf"
    },
    {
      "rfilename": "Qwen3-4B-Q3_K_M_imatrix.gguf"
    },
    {
      "rfilename": "Qwen3-4B-Q4_K_M.gguf"
    },
    {
      "rfilename": "Qwen3-4B-Q4_K_M_imatrix.gguf"
    },
    {
      "rfilename": "Qwen3-4B-Q5_K_M.gguf"
    },
    {
      "rfilename": "Qwen3-4B-Q6_K.gguf"
    },
    {
      "rfilename": "Qwen3-4B-Q8_0.gguf"
    },
    {
      "rfilename": "README.md"
    },
    {
      "rfilename": "assets/benchmarkhf-dark-mode-only.png"
    },
    {
      "rfilename": "assets/benchmarkhf-light-mode-only.png"
    },
    {
      "rfilename": "bench/bench_F16_v2.md"
    },
    {
      "rfilename": "bench/bench_Q3_K_M_imatrix_v2.md"
    },
    {
      "rfilename": "bench/bench_Q3_K_M_v2.md"
    },
    {
      "rfilename": "bench/bench_Q4_K_M_imatrix_v2.md"
    },
    {
      "rfilename": "bench/bench_Q4_K_M_v2.md"
    },
    {
      "rfilename": "bench/bench_Q5_K_M_v2.md"
    },
    {
      "rfilename": "bench/bench_Q6_K_v2.md"
    },
    {
      "rfilename": "bench/bench_Q8_0_v2.md"
    },
    {
      "rfilename": "bench/perp_F16.log"
    },
    {
      "rfilename": "bench/perp_Q3_K_M.log"
    },
    {
      "rfilename": "bench/perp_Q3_K_M_imatrix.log"
    },
    {
      "rfilename": "bench/perp_Q4_K_M.log"
    },
    {
      "rfilename": "bench/perp_Q4_K_M_imatrix.log"
    },
    {
      "rfilename": "bench/perp_Q5_K_M.log"
    },
    {
      "rfilename": "bench/perp_Q6_K.log"
    },
    {
      "rfilename": "bench/perp_Q8_0.log"
    },
    {
      "rfilename": "bench/run_bench.sh"
    },
    {
      "rfilename": "data/results.tsv"
    },
    {
      "rfilename": "data/wiki.test.raw"
    }
  ],
  "tags": [
    "llama.cpp",
    "gguf",
    "quantization",
    "qwen3",
    "benchmark",
    "low-ram-inference",
    "cpu-inference",
    "perplexity",
    "imatrix",
    "k-quants",
    "text-generation",
    "en",
    "dataset:wikitext-2",
    "base_model:Qwen/Qwen3-4B",
    "base_model:quantized:Qwen/Qwen3-4B",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ]
}

Text

This source's terms allow its title, its values and a link here, not its text. It is at https://huggingface.co/b4ph/qwen3-4b-lowram-bench.