Published by baidu. No machine on this network has measured this family yet. The members below are what the catalog knows exists; nothing about what they can do is claimed here until somebody runs one.
what it takes, what it returns
image + text → text
Declared by the network’s catalog, not measured — a signature says what this family would be asked. Whether it answered is the signed capability flags on each member.
0 of 27 builds measured · 27 still open
Qianfan-OCR BASE8 known builds · not measured
Qianfan-OCR-8bit1 known build · not measured
Qianfan-OCR-GGUF2 known builds · not measured
Qianfan-OCR1 known build · not measured
Qianfan-OCR-GGUF6 known builds · not measured
Qianfan-OCR1 known build · not measured
Qianfan-OCR1 known build · not measured
Qianfan-OCR1 known build · not measured
Qianfan-OCR1 known build · not measured
Qianfan-OCR1 known build · not measured
Qianfan-OCR-oQ41 known build · not measured
Qianfan-OCR-oQ51 known build · not measured
Qianfan-OCR-oQ61 known build · not measured
Qianfan-OCR-oQ81 known build · not measured
Builds this network knows of
Declared, not measured — this is what the catalog says exists and what it would cost a machine to hold. Nothing here is signed, and none of it claims the build works.
how much memory does your machine have
27 of 27 builds fit a 16 GB machine — budgeting 70% of it, or 11.2 GiB, because the cache and the runtime want the rest.
hf.co/Reza2kn/Qianfan-OCR-GGUF:Q2_KQ2_Kollamaquantized by Reza2kn
1.7 GiB
hf.co/Mungert/Qianfan-OCR-GGUF:IQ3_XXSIQ3_XXSollamaderived by Mungert
1.9 GiB
hf.co/Reza2kn/Qianfan-OCR-GGUF:Q3_K_SQ3_K_Sollamaquantized by Reza2kn
1.9 GiB
hf.co/Mungert/Qianfan-OCR-GGUF:IQ4_NLIQ4_NLollamaderived by Mungert
2.3 GiB
hf.co/Reza2kn/Qianfan-OCR-GGUF:Q4_0Q4_0ollamaquantized by Reza2kn
2.4 GiB
hf.co/Reza2kn/Qianfan-OCR-GGUF:Q4_K_MQ4_K_Mollamaquantized by Reza2kn
2.5 GiB
hf.co/Mungert/Qianfan-OCR-GGUF:Q4_K_SQ4_K_Sollamaderived by Mungert
2.6 GiB
hf.co/Mungert/Qianfan-OCR-GGUF:Q4_K_MQ4_K_Mollamaderived by Mungert
2.8 GiB
jason1966/Qianfan-OCR-MLX-4bit4BITmlxquantized by jason1966
2.9 GiB
beaupi/Qianfan-OCR-oQ44BITvllmderived by beaupi
3.0 GiB
beaupi/Qianfan-OCR-oQ55BITvllmderived by beaupi
3.5 GiB
beaupi/Qianfan-OCR-oQ66BITvllmderived by beaupi
4.0 GiB
hf.co/Reza2kn/Qianfan-OCR-GGUF:Q8_0Q8_0ollamaquantized by Reza2kn
4.4 GiB
hf.co/ggml-org/Qianfan-OCR-GGUF:Q8_0Q8_0ollamaderived by ggml-org
4.4 GiB
beaupi/Qianfan-OCR-oQ88BITvllmderived by beaupi
5.0 GiB
FriskyFennec/Qianfan-OCR-8bitBITSANDBYTESvllmderived by FriskyFennec
5.5 GiB
hf.co/Mungert/Qianfan-OCR-GGUF:Q8_0Q8_0ollamaderived by Mungert
6.3 GiB
hf.co/Reza2kn/Qianfan-OCR-GGUF:BF16BF16ollamaquantized by Reza2kn
8.2 GiB
hf.co/ggml-org/Qianfan-OCR-GGUF:F16F16ollamaderived by ggml-org
8.2 GiB
hf.co/Mungert/Qianfan-OCR-GGUF:BF16BF16ollamaderived by Mungert
8.2 GiB
baidu/Qianfan-OCRBF16vllmpublished by baidu
8.8 GiB
Jinstudio/Qianfan-OCRBF16vllmderived by Jinstudio
8.8 GiB
rootlocalghost/Qianfan-OCRBF16vllmderived by rootlocalghost
8.8 GiB
singersalt/Qianfan-OCRBF16vllmderived by singersalt
8.8 GiB
Trkaga/Qianfan-OCRBF16vllmderived by Trkaga
8.8 GiB
XXINTUANDDUI/Qianfan-OCRBF16vllmderived by XXINTUANDDUI
8.8 GiB
zhoude/Qianfan-OCRBF16vllmderived by zhoude
8.8 GiB
Sizes are what the catalog declares, not what a machine measured — fitting on disk is necessary and not sufficient. Nobody here has run these on your machine, and this narrows the candidates rather than certifying one.
the same builds, by member
Qianfan-OCR BASE
hf.co/Reza2kn/Qianfan-OCR-GGUF:Q2_KQ2_Kollama1.7 GiB on diskquantized by Reza2kn
hf.co/Reza2kn/Qianfan-OCR-GGUF:Q3_K_SQ3_K_Sollama1.9 GiB on diskquantized by Reza2kn
hf.co/Reza2kn/Qianfan-OCR-GGUF:Q4_0Q4_0ollama2.4 GiB on diskquantized by Reza2kn
hf.co/Reza2kn/Qianfan-OCR-GGUF:Q4_K_MQ4_K_Mollama2.5 GiB on diskquantized by Reza2kn
jason1966/Qianfan-OCR-MLX-4bit4BITmlx2.9 GiB on diskquantized by jason1966
hf.co/Reza2kn/Qianfan-OCR-GGUF:Q8_0Q8_0ollama4.4 GiB on diskquantized by Reza2kn
hf.co/Reza2kn/Qianfan-OCR-GGUF:BF16BF16ollama8.2 GiB on diskquantized by Reza2kn
baidu/Qianfan-OCRBF16vllm8.8 GiB on diskpublished by baidu
Qianfan-OCR-8bit
FriskyFennec/Qianfan-OCR-8bitBITSANDBYTESvllm5.5 GiB on diskderived by FriskyFennec
Qianfan-OCR-GGUF
hf.co/ggml-org/Qianfan-OCR-GGUF:Q8_0Q8_0ollama4.4 GiB on diskderived by ggml-org
hf.co/ggml-org/Qianfan-OCR-GGUF:F16F16ollama8.2 GiB on diskderived by ggml-org
Qianfan-OCR
Jinstudio/Qianfan-OCRBF16vllm8.8 GiB on diskderived by Jinstudio
Qianfan-OCR-GGUF
hf.co/Mungert/Qianfan-OCR-GGUF:IQ3_XXSIQ3_XXSollama1.9 GiB on diskderived by Mungert
hf.co/Mungert/Qianfan-OCR-GGUF:IQ4_NLIQ4_NLollama2.3 GiB on diskderived by Mungert
hf.co/Mungert/Qianfan-OCR-GGUF:Q4_K_SQ4_K_Sollama2.6 GiB on diskderived by Mungert
hf.co/Mungert/Qianfan-OCR-GGUF:Q4_K_MQ4_K_Mollama2.8 GiB on diskderived by Mungert
hf.co/Mungert/Qianfan-OCR-GGUF:Q8_0Q8_0ollama6.3 GiB on diskderived by Mungert
hf.co/Mungert/Qianfan-OCR-GGUF:BF16BF16ollama8.2 GiB on diskderived by Mungert
Qianfan-OCR
rootlocalghost/Qianfan-OCRBF16vllm8.8 GiB on diskderived by rootlocalghost
Qianfan-OCR
singersalt/Qianfan-OCRBF16vllm8.8 GiB on diskderived by singersalt
Qianfan-OCR
Trkaga/Qianfan-OCRBF16vllm8.8 GiB on diskderived by Trkaga
Qianfan-OCR
XXINTUANDDUI/Qianfan-OCRBF16vllm8.8 GiB on diskderived by XXINTUANDDUI
Qianfan-OCR
zhoude/Qianfan-OCRBF16vllm8.8 GiB on diskderived by zhoude
Qianfan-OCR-oQ4
beaupi/Qianfan-OCR-oQ44BITvllm3.0 GiB on diskderived by beaupi
Qianfan-OCR-oQ5
beaupi/Qianfan-OCR-oQ55BITvllm3.5 GiB on diskderived by beaupi
Qianfan-OCR-oQ6
beaupi/Qianfan-OCR-oQ66BITvllm4.0 GiB on diskderived by beaupi
Qianfan-OCR-oQ8
beaupi/Qianfan-OCR-oQ88BITvllm5.0 GiB on diskderived by beaupi
ask your own gram
Your concierge can answer this from the network rather than from this page. The ask carries the operator id, so it resolves to a capability and an engine — not to a name somebody has to recognise.
What has this network measured about the Qianfan-OCR family (epn.family.qianfan-ocr), and can my gram run any of it? See /inferences/qianfan-ocr