model family

Qwen 3.8

Published by Qwen. 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 → texttext → 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 58 builds measured · 58 still open

Qwen 3.8 2-4T-A95B1 known build · not measured

Qwen 3.8 27B14 known builds · not measured

Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU6 known builds · not measured

Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF4 known builds · not measured

Huihui-Qwen3.8-27B-abliterated-GGUF7 known builds · not measured

Qwen3.8-27B-Uncensored-GGUF5 known builds · not measured

Qwen3.8-27B-Uncensored-MLX1 known build · not measured

Dirk-Qwen3.8-27B-GGUF5 known builds · not measured

Swift-1.5-Qwen3.8-27b3 known builds · not measured

Qwen3.8-27B-MTPLX-Optimized-Speed1 known build · not measured

Qwen 3.8 FLASH-NEXT2 known builds · not measured

Qwen3.8-Flash-Next-GSQ-RCO-GGUF3 known builds · not measured

Qwen3.8-Flash-Next-oQ4e-mtp1 known build · not measured

Qwen3.8-Flash-Next-REAP-288-MLX-4bit1 known build · not measured

Qwen3.8-Flash-Next-MTPLX-Optimized-Speed1 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

13 of 58 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/unsloth/Qwen3.8-27B-GGUF:IQ1_SIQ1_Sollamaquantized by unsloth
5.8 GiB
hf.co/unsloth/Qwen3.8-27B-GGUF:IQ2_XXSIQ2_XXSollamaquantized by unsloth
6.8 GiB
hf.co/huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF:IQ2IQ2ollamaderived by huihui-ai
7.4 GiB
hf.co/huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF:IQ2_XSIQ2_XSollamaderived by huihui-ai
7.8 GiB
hf.co/ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF:IQ2_XSIQ2_XSollamaderived by ukisai
7.8 GiB
hf.co/peculiar-ragdoll/Dirk-Qwen3.8-27B-GGUF:IQ2_XSIQ2_XSollamaderived by peculiar-ragdoll
8.2 GiB
hf.co/ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF:IQ3_XXSIQ3_XXSollamaderived by ukisai
9.4 GiB
hf.co/HauhauCS/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF:IQ2_MIQ2_Mollamaderived by HauhauCS
9.6 GiB
hf.co/peculiar-ragdoll/Dirk-Qwen3.8-27B-GGUF:IQ3_XXSIQ3_XXSollamaderived by peculiar-ragdoll
9.7 GiB
hf.co/JonathanColetti/Qwen3.8-27B-Uncensored-GGUF:IQ2_MIQ2_Mollamaderived by JonathanColetti
9.9 GiB
hf.co/unsloth/Qwen3.8-27B-GGUF:IQ3_XXSIQ3_XXSollamaquantized by unsloth
10.2 GiB
hf.co/huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF:IQ3_XXSIQ3_XXSollamaderived by huihui-ai
10.6 GiB
hf.co/ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF:IQ3_SIQ3_Sollamaderived by ukisai
11.0 GiB
hf.co/peculiar-ragdoll/Dirk-Qwen3.8-27B-GGUF:IQ3_SIQ3_Sollamaderived by peculiar-ragdoll
11.3 GiB
hf.co/DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF:IQ2_MIQ2_Mollamaderived by DavidAU
11.3 GiB
hf.co/HauhauCS/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF:IQ3_XSIQ3_XSollamaderived by HauhauCS
11.3 GiB
hf.co/HauhauCS/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF:Q3_K_PQ3_K_Pollamaderived by HauhauCS
12.5 GiB
hf.co/DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF:IQ3_MIQ3_Mollamaderived by DavidAU
13.5 GiB
hf.co/JonathanColetti/Qwen3.8-27B-Uncensored-GGUF:IQ4_XSIQ4_XSollamaderived by JonathanColetti
14.3 GiB
hf.co/unsloth/Qwen3.8-27B-GGUF:Q4_K_SQ4_K_Sollamaquantized by unsloth
14.3 GiB
hf.co/peculiar-ragdoll/Dirk-Qwen3.8-27B-GGUF:Q4_K_SQ4_K_Sollamaderived by peculiar-ragdoll
14.3 GiB
hf.co/huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF:Q4_K_SQ4_K_Sollamaderived by huihui-ai
14.6 GiB
lmstudio-community/Qwen3.8-27B-MLX-4bit4BITmlxquantized by lmstudio-community
15.0 GiB
hf.co/unsloth/Qwen3.8-27B-GGUF:Q4_K_MQ4_K_Mollamaquantized by unsloth
15.3 GiB
hf.co/peculiar-ragdoll/Dirk-Qwen3.8-27B-GGUF:Q4_K_MQ4_K_Mollamaderived by peculiar-ragdoll
15.3 GiB
hf.co/huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF:Q4_K_MQ4_K_Mollamaderived by huihui-ai
15.4 GiB
hf.co/JonathanColetti/Qwen3.8-27B-Uncensored-GGUF:Q4_K_MQ4_K_Mollamaderived by JonathanColetti
15.7 GiB
hf.co/DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF:IQ4_XSIQ4_XSollamaderived by DavidAU
15.9 GiB
hf.co/DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF:Q4_K_SQ4_K_Sollamaderived by DavidAU
16.3 GiB
hf.co/DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF:Q4_K_MQ4_K_Mollamaderived by DavidAU
17.2 GiB
hf.co/JonathanColetti/Qwen3.8-27B-Uncensored-GGUF:Q5_K_MQ5_K_Mollamaderived by JonathanColetti
18.2 GiB
Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed4BITmlxderived by Youssofal
19.3 GiB
cyankiwi/Qwen3.8-27B-AWQ-INT4W4A16vllmquantized by cyankiwi
19.6 GiB
RadixArk/Qwen3.8-27B-NVFP4NVFP4vllmquantized by RadixArk
20.4 GiB
lmstudio-community/Qwen3.8-27B-MLX-6bit6BITmlxquantized by lmstudio-community
21.2 GiB
hf.co/HauhauCS/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF:Q6_K_PQ6_K_Pollamaderived by HauhauCS
24.1 GiB
hf.co/unsloth/Qwen3.8-27B-GGUF:Q8_0Q8_0ollamaquantized by unsloth
27.1 GiB
hf.co/huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF:Q8_0Q8_0ollamaderived by huihui-ai
27.1 GiB
hf.co/JonathanColetti/Qwen3.8-27B-Uncensored-GGUF:Q8_0Q8_0ollamaderived by JonathanColetti
27.1 GiB
lmstudio-community/Qwen3.8-27B-MLX-8bit8BITmlxquantized by lmstudio-community
27.5 GiB
hf.co/DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF:Q8_0Q8_0ollamaderived by DavidAU
28.2 GiB
Qwen/Qwen3.8-27B-FP8FP8vllmpublished by Qwen
28.7 GiB
hf.co/ggml-org/Qwen3.8-27B-GGUF:BF16BF16ollamaquantized by ggml-org
50.1 GiB
hf.co/huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF:F16F16ollamaderived by huihui-ai
50.1 GiB
unsloth/Qwen3.8-27B-GGUF:BF16BF16llamacppquantized by unsloth
50.9 GiB
ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF:Q2_0Q2_0llamacppderived by ISTA-DASLab
61.9 GiB
SC117/Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF:Q2_0Q2_0llamacppderived by SC117
62.2 GiB
ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF:IQ2_XSIQ2_XSllamacppderived by ISTA-DASLab
63.4 GiB
SC117/Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF:IQ2_XSIQ2_XSllamacppderived by SC117
63.8 GiB
sh0wie/Qwen3.8-Flash-Next-REAP-288-MLX-4bit4BITmlxderived by sh0wie
68.4 GiB
ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF:IQ3_XXSIQ3_XXSllamacppderived by ISTA-DASLab
70.6 GiB
SC117/Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF:IQ3_XXSIQ3_XXSllamacppderived by SC117
70.9 GiB
orcarouter/Qwen3.8-27B-Uncensored-MLX4BITmlxderived by orcarouter
88.1 GiB
Jundot/Qwen3.8-Flash-Next-oQ4e-mtp4BITmlxderived by Jundot
100.1 GiB
Youssofal/Qwen3.8-Flash-Next-MTPLX-Optimized-Speed4BITmlxderived by Youssofal
107.1 GiB
RadixArk/Qwen3.8-Flash-Next-NVFP4NVFP4vllmquantized by RadixArk
125.9 GiB
Qwen/Qwen3.8-Flash-Next-FP8FP8vllmpublished by Qwen
172.8 GiB
Qwen/Qwen3.8-2.4T-A95BBF16vllmpublished by Qwen
4556.4 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

Qwen 3.8 2-4T-A95B

Qwen/Qwen3.8-2.4T-A95BBF16vllm4556.4 GiB on diskpublished by Qwen

Qwen 3.8 27B

hf.co/unsloth/Qwen3.8-27B-GGUF:IQ1_SIQ1_Sollama5.8 GiB on diskquantized by unsloth

hf.co/unsloth/Qwen3.8-27B-GGUF:IQ2_XXSIQ2_XXSollama6.8 GiB on diskquantized by unsloth

hf.co/unsloth/Qwen3.8-27B-GGUF:IQ3_XXSIQ3_XXSollama10.2 GiB on diskquantized by unsloth

hf.co/unsloth/Qwen3.8-27B-GGUF:Q4_K_SQ4_K_Sollama14.3 GiB on diskquantized by unsloth

lmstudio-community/Qwen3.8-27B-MLX-4bit4BITmlx15.0 GiB on diskquantized by lmstudio-community

hf.co/unsloth/Qwen3.8-27B-GGUF:Q4_K_MQ4_K_Mollama15.3 GiB on diskquantized by unsloth

cyankiwi/Qwen3.8-27B-AWQ-INT4W4A16vllm19.6 GiB on diskquantized by cyankiwi

RadixArk/Qwen3.8-27B-NVFP4NVFP4vllm20.4 GiB on diskquantized by RadixArk

lmstudio-community/Qwen3.8-27B-MLX-6bit6BITmlx21.2 GiB on diskquantized by lmstudio-community

hf.co/unsloth/Qwen3.8-27B-GGUF:Q8_0Q8_0ollama27.1 GiB on diskquantized by unsloth

lmstudio-community/Qwen3.8-27B-MLX-8bit8BITmlx27.5 GiB on diskquantized by lmstudio-community

Qwen/Qwen3.8-27B-FP8FP8vllm28.7 GiB on diskpublished by Qwen

hf.co/ggml-org/Qwen3.8-27B-GGUF:BF16BF16ollama50.1 GiB on diskquantized by ggml-org

unsloth/Qwen3.8-27B-GGUF:BF16BF16llamacpp50.9 GiB on diskquantized by unsloth

Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU

hf.co/DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF:IQ2_MIQ2_Mollama11.3 GiB on diskderived by DavidAU

hf.co/DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF:IQ3_MIQ3_Mollama13.5 GiB on diskderived by DavidAU

hf.co/DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF:IQ4_XSIQ4_XSollama15.9 GiB on diskderived by DavidAU

hf.co/DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF:Q4_K_SQ4_K_Sollama16.3 GiB on diskderived by DavidAU

hf.co/DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF:Q4_K_MQ4_K_Mollama17.2 GiB on diskderived by DavidAU

hf.co/DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF:Q8_0Q8_0ollama28.2 GiB on diskderived by DavidAU

Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF

hf.co/HauhauCS/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF:IQ2_MIQ2_Mollama9.6 GiB on diskderived by HauhauCS

hf.co/HauhauCS/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF:IQ3_XSIQ3_XSollama11.3 GiB on diskderived by HauhauCS

hf.co/HauhauCS/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF:Q3_K_PQ3_K_Pollama12.5 GiB on diskderived by HauhauCS

hf.co/HauhauCS/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF:Q6_K_PQ6_K_Pollama24.1 GiB on diskderived by HauhauCS

Huihui-Qwen3.8-27B-abliterated-GGUF

hf.co/huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF:IQ2IQ2ollama7.4 GiB on diskderived by huihui-ai

hf.co/huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF:IQ2_XSIQ2_XSollama7.8 GiB on diskderived by huihui-ai

hf.co/huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF:IQ3_XXSIQ3_XXSollama10.6 GiB on diskderived by huihui-ai

hf.co/huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF:Q4_K_SQ4_K_Sollama14.6 GiB on diskderived by huihui-ai

hf.co/huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF:Q4_K_MQ4_K_Mollama15.4 GiB on diskderived by huihui-ai

hf.co/huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF:Q8_0Q8_0ollama27.1 GiB on diskderived by huihui-ai

hf.co/huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF:F16F16ollama50.1 GiB on diskderived by huihui-ai

Qwen3.8-27B-Uncensored-GGUF

hf.co/JonathanColetti/Qwen3.8-27B-Uncensored-GGUF:IQ2_MIQ2_Mollama9.9 GiB on diskderived by JonathanColetti

hf.co/JonathanColetti/Qwen3.8-27B-Uncensored-GGUF:IQ4_XSIQ4_XSollama14.3 GiB on diskderived by JonathanColetti

hf.co/JonathanColetti/Qwen3.8-27B-Uncensored-GGUF:Q4_K_MQ4_K_Mollama15.7 GiB on diskderived by JonathanColetti

hf.co/JonathanColetti/Qwen3.8-27B-Uncensored-GGUF:Q5_K_MQ5_K_Mollama18.2 GiB on diskderived by JonathanColetti

hf.co/JonathanColetti/Qwen3.8-27B-Uncensored-GGUF:Q8_0Q8_0ollama27.1 GiB on diskderived by JonathanColetti

Qwen3.8-27B-Uncensored-MLX

orcarouter/Qwen3.8-27B-Uncensored-MLX4BITmlx88.1 GiB on diskderived by orcarouter

Dirk-Qwen3.8-27B-GGUF

hf.co/peculiar-ragdoll/Dirk-Qwen3.8-27B-GGUF:IQ2_XSIQ2_XSollama8.2 GiB on diskderived by peculiar-ragdoll

hf.co/peculiar-ragdoll/Dirk-Qwen3.8-27B-GGUF:IQ3_XXSIQ3_XXSollama9.7 GiB on diskderived by peculiar-ragdoll

hf.co/peculiar-ragdoll/Dirk-Qwen3.8-27B-GGUF:IQ3_SIQ3_Sollama11.3 GiB on diskderived by peculiar-ragdoll

hf.co/peculiar-ragdoll/Dirk-Qwen3.8-27B-GGUF:Q4_K_SQ4_K_Sollama14.3 GiB on diskderived by peculiar-ragdoll

hf.co/peculiar-ragdoll/Dirk-Qwen3.8-27B-GGUF:Q4_K_MQ4_K_Mollama15.3 GiB on diskderived by peculiar-ragdoll

Swift-1.5-Qwen3.8-27b

hf.co/ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF:IQ2_XSIQ2_XSollama7.8 GiB on diskderived by ukisai

hf.co/ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF:IQ3_XXSIQ3_XXSollama9.4 GiB on diskderived by ukisai

hf.co/ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF:IQ3_SIQ3_Sollama11.0 GiB on diskderived by ukisai

Qwen3.8-27B-MTPLX-Optimized-Speed

Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed4BITmlx19.3 GiB on diskderived by Youssofal

Qwen 3.8 FLASH-NEXT

RadixArk/Qwen3.8-Flash-Next-NVFP4NVFP4vllm125.9 GiB on diskquantized by RadixArk

Qwen/Qwen3.8-Flash-Next-FP8FP8vllm172.8 GiB on diskpublished by Qwen

Qwen3.8-Flash-Next-GSQ-RCO-GGUF

SC117/Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF:Q2_0Q2_0llamacpp62.2 GiB on diskderived by SC117

SC117/Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF:IQ2_XSIQ2_XSllamacpp63.8 GiB on diskderived by SC117

SC117/Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF:IQ3_XXSIQ3_XXSllamacpp70.9 GiB on diskderived by SC117

Qwen3.8-Flash-Next-GSQ-RCO-GGUF

ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF:Q2_0Q2_0llamacpp61.9 GiB on diskderived by ISTA-DASLab

ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF:IQ2_XSIQ2_XSllamacpp63.4 GiB on diskderived by ISTA-DASLab

ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF:IQ3_XXSIQ3_XXSllamacpp70.6 GiB on diskderived by ISTA-DASLab

Qwen3.8-Flash-Next-oQ4e-mtp

Jundot/Qwen3.8-Flash-Next-oQ4e-mtp4BITmlx100.1 GiB on diskderived by Jundot

Qwen3.8-Flash-Next-REAP-288-MLX-4bit

sh0wie/Qwen3.8-Flash-Next-REAP-288-MLX-4bit4BITmlx68.4 GiB on diskderived by sh0wie

Qwen3.8-Flash-Next-MTPLX-Optimized-Speed

Youssofal/Qwen3.8-Flash-Next-MTPLX-Optimized-Speed4BITmlx107.1 GiB on diskderived by Youssofal

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 Qwen 3.8 family (epn.family.qwen-3-8), and can my gram run any of it? See /inferences/qwen-3-8

open a gramx with this ask →epn.family.qwen-3-8