Qwen3.8 Qwen

LLMs MoE 3 members 3,189 derivatives on the Hub Last verified 2026-10-25 RSS

quantized: 2,079adapter: 256finetune: 822merge: 32

Which ones matter

Qwen3.8-27B Qwen/Qwen3.8-27B
Highest candidate score in the family (140.169); 7 providers serving it.
Qwen3.8-27B-GGUF unsloth/Qwen3.8-27B-GGUF
Most downloaded quantization (20,668,813 all-time, by unsloth).

Picks are rule-based from observed data (score, downloads, size, hosting); they are not quality verdicts.

Members 3

#	Model	Org	Role	Params	Band	MoE	License	Context	Providers	Price from	Likes	Likes 7d	Downloads 30d	Modified
1	Qwen3.8-27B	Qwen	Original model	27.8B	L	dense	Apache 2.0	256K	7	$0.02	18.3k	+434	7.9M	2026-08-14
38	Qwen3.8-Flash-Next	Qwen	Original model	180B	XXL	MoE	Qwen License (qwen-communit…	256K	2	$0.15	6.4k	+147	3M	2026-08-27
118	Qwen3.8-2.4T-A95B	Qwen	Original model	2.45T / 95B	XXL	MoE	Qwen License (qwen3.8-max)	256K	5	$2.00	1.3k	+12	25.4k	2026-08-12

Variants 150 shown of 3,189

Quantizations, fine-tunes, merges, and adapters of any member, ranked by downloads + likes. Filter by relation, quant family, or size band.

Variant	Of	Relation	Quant	Params	Band	License	Author	Likes	Downloads
unsloth/Qwen3.8-27B-GGUF	Qwen/Qwen3.8-27B	quantized	GGUF	—	—	apache-2.0	unsloth	5.3k	20.7M
Qwen/Qwen3.8-27B-FP8	Qwen/Qwen3.8-27B	quantized	-FP8	27.8B	L	apache-2.0	Qwen	941	14.3M
lmstudio-community/Qwen3.8-27B-MLX-4bit	Qwen/Qwen3.8-27B	quantized	MLX	27.4B	L	apache-2.0	lmstudio-community	112	10.2M
lmstudio-community/Qwen3.8-27B-MLX-8bit	Qwen/Qwen3.8-27B	quantized	MLX	27.4B	L	apache-2.0	lmstudio-community	50	9.8M
lmstudio-community/Qwen3.8-27B-MLX-6bit	Qwen/Qwen3.8-27B	quantized	MLX	27.4B	L	apache-2.0	lmstudio-community	38	9.7M
lmstudio-community/Qwen3.8-27B-MLX-5bit	Qwen/Qwen3.8-27B	quantized	MLX	27.4B	L	apache-2.0	lmstudio-community	16	9.6M
cdiamond/Qwen3.8-27B-iMatrix-NVFP4-MTP-GGUF	Qwen/Qwen3.8-27B	quantized	iMatrix	—	—	apache-2.0	cdiamond	43	7.6M
ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF	Qwen/Qwen3.8-Flash-Next	quantized	GGUF	—	—	apache-2.0	ISTA-DASLab	1k	7M
JonathanColetti/Qwen3.8-27B-Uncensored-GGUF	Qwen/Qwen3.8-27B	quantized	GGUF	—	—	apache-2.0	JonathanColetti	1.7k	6.5M
unsloth/Qwen3.8-27B-NVFP4	Qwen/Qwen3.8-27B	quantized	NVFP4	19.9B	L	apache-2.0	unsloth	522	6.4M
huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF	Qwen/Qwen3.8-27B	quantized	GGUF	—	—	apache-2.0	huihui-ai	1.5k	6.1M
prism-ml/Ternary-Bonsai-2-27B-gguf	Qwen/Qwen3.8-27B	quantized	gguf	—	—	apache-2.0	prism-ml	2.8k	5.4M
HauhauCS/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF	Qwen/Qwen3.8-27B	quantized	GGUF	—	—	apache-2.0	HauhauCS	2.1k	5.3M
lmstudio-community/Qwen3.8-27B-GGUF	Qwen/Qwen3.8-27B	quantized	GGUF	—	—	apache-2.0	lmstudio-community	76	4.7M
ggml-org/Qwen3.8-27B-GGUF	Qwen/Qwen3.8-27B	quantized	GGUF	—	—	apache-2.0	ggml-org	137	4.1M
RadixArk/Qwen3.8-27B-NVFP4	Qwen/Qwen3.8-27B	quantized	NVFP4	18.2B	L	apache-2.0	RadixArk	118	3.9M
0bserverx/Qwen3.8-27B-Heretic-Abliterated-Uncensored-GGUF	Qwen/Qwen3.8-27B	quantized	GGUF	—	—	apache-2.0	0bserverx	748	3.5M
unsloth/Qwen3.8-Flash-Next-GGUF	Qwen/Qwen3.8-Flash-Next	quantized	GGUF	—	—	other	unsloth	1.3k	2.9M
ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF	Qwen/Qwen3.8-27B	quantized	GGUF	—	—	apache-2.0	ISTA-DASLab	2.3k	2.8M
cyankiwi/Qwen3.8-27B-AWQ-INT4	Qwen/Qwen3.8-27B	quantized	AWQ	27.8B	L	apache-2.0	cyankiwi	123	2.8M
autotrust/JEV-27B-VL	Qwen/Qwen3.8-27B	adapter	—	27.8B	L	apache-2.0	autotrust	1.2k	2.4M
peculiar-ragdoll/Dirk-Qwen3.8-27B-GGUF	Qwen/Qwen3.8-27B	quantized	GGUF	—	—	apache-2.0	peculiar-ragdoll	246	2.3M
byteshape/Qwen3.8-27B-GGUF	Qwen/Qwen3.8-27B	quantized	GGUF	—	—	apache-2.0	byteshape	180	2.2M
Inferact/Qwen3.8-27B-NVFP4	Qwen/Qwen3.8-27B	quantized	NVFP4	17.6B	L	apache-2.0	Inferact	21	2.1M
OBLITERATUS/Qwen3.8-27B-OBLITERATED	Qwen/Qwen3.8-27B	quantized	GGUF	27.8B	L	apache-2.0	OBLITERATUS	1.5k	2M
gittensor-model-hub/Qwen3.8-27B-NVFP4-RTX5090	Qwen/Qwen3.8-27B	quantized	NVFP4	14.6B	L	apache-2.0	gittensor-model-hub	173	1.3M
orcarouter/Qwen3.8-Flash-Next-Uncensored-GGUF	Qwen/Qwen3.8-Flash-Next	quantized	GGUF	—	—	apache-2.0	orcarouter	1.1k	1.2M
z-lab/Qwen3.8-27B-DFlash2-GGUF	Qwen/Qwen3.8-27B	quantized	GGUF	—	—	apache-2.0	z-lab	155	1.1M
bartowski/Qwen3.8-27B-GGUF	Qwen/Qwen3.8-27B	quantized	GGUF	—	—	apache-2.0	bartowski	214	1.1M
mlx-community/Qwen3.8-27B-4bit	Qwen/Qwen3.8-27B	quantized	-4bit	27.4B	L	apache-2.0	mlx-community	224	1.1M
AtomicChat/Qwen3.8-Flash-Next-GGUF	Qwen/Qwen3.8-Flash-Next	quantized	GGUF	—	—	other	AtomicChat	197	1M
empero-ai/Qwen3.8-27B-Ridge-GGUF	Qwen/Qwen3.8-27B	quantized	GGUF	—	—	apache-2.0	empero-ai	363	998.2k
ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF	Qwen/Qwen3.8-Flash-Next	quantized	GGUF	—	—	apache-2.0	ISTA-DASLab	485	972.8k
RedHatAI/Qwen3.8-27B-INT4	Qwen/Qwen3.8-27B	quantized	INT4	27.4B	L	apache-2.0	RedHatAI	57	862.7k
incoai/Qwen3.8-27B-DFlash2	Qwen/Qwen3.8-27B	finetune	—	1.92B	S	apache-2.0	incoai	289	850.4k
RadixArk/Qwen3.8-Flash-Next-NVFP4	Qwen/Qwen3.8-Flash-Next	quantized	NVFP4	120B	XXL	other	RadixArk	140	850.3k
agentionai/Qwen3.8-27B-AP-GGUF	Qwen/Qwen3.8-27B	quantized	GGUF	—	—	apache-2.0	agentionai	93	808.8k
nvidia/Qwen3.8-27B-NVFP4	Qwen/Qwen3.8-27B	quantized	NVFP4	18.2B	L	apache-2.0	nvidia	211	752.7k
sakamakismile/Qwen3.8-27B-MTP-NVFP4	Qwen/Qwen3.8-27B	quantized	NVFP4	27.4B	L	apache-2.0	sakamakismile	45	743.8k
philbert440/Qwen3.8-27B-W4A16-AWQ	Qwen/Qwen3.8-27B	quantized	-W4A16	27.4B	L	apache-2.0	philbert440	32	739.3k
orcarouter/Qwen3.8-27B-Uncensored-FP8	Qwen/Qwen3.8-27B	quantized	-FP8	27.8B	L	apache-2.0	orcarouter	1.8k	642.3k
Qwen/Qwen3.8-Flash-Next-FP8	Qwen/Qwen3.8-Flash-Next	quantized	-FP8	180B	XXL	other	Qwen	276	705.8k
nvidia/Qwen3.8-Flash-Next-NVFP4	Qwen/Qwen3.8-Flash-Next	quantized	NVFP4	120B	XXL	other	nvidia	387	588.5k
unsloth/Qwen3.8-27B	Qwen/Qwen3.8-27B	finetune	—	27.8B	L	apache-2.0	unsloth	55	597.9k
orcarouter/Qwen3.8-27B-Uncensored-GGUF	Qwen/Qwen3.8-27B	quantized	GGUF	—	—	apache-2.0	orcarouter	1.6k	482.1k
neroued/Qwen3.8-27B-NInfer	Qwen/Qwen3.8-27B	quantized	—	—	—	apache-2.0	neroued	80	532.7k
neroued/Qwen3.8-27B-nvfp4-NInfer	Qwen/Qwen3.8-27B	quantized	nvfp4	—	—	apache-2.0	neroued	113	496.9k
z-lab/Qwen3.8-27B-DFlash2	Qwen/Qwen3.8-27B	finetune	—	1.92B	S	apache-2.0	z-lab	318	484.6k
RadixArk/Qwen3.8-27B-NVFP4-BF16-LMHead	Qwen/Qwen3.8-27B	quantized	NVFP4	18.2B	L	apache-2.0	RadixArk	26	490.1k
huihui-ai/Huihui-Qwen3.8-Flash-Next-abliterated-GGUF	Qwen/Qwen3.8-Flash-Next	quantized	GGUF	—	—	other	huihui-ai	186	458.7k
DavidAU/Qwen3.8-27B-Turbo-Brilliance-50X-Reasoning-Instruct-NEO-MAX-MTP-GGUF	Qwen/Qwen3.8-27B	quantized	GGUF	—	—	apache-2.0	DavidAU	235	426k
AtomicChat/Qwen3.8-27B-GGUF	Qwen/Qwen3.8-27B	quantized	GGUF	—	—	—	AtomicChat	178	390k
orcarouter/Qwen3.8-27B-Uncensored-MLX	Qwen/Qwen3.8-27B	quantized	MLX	27.4B	L	apache-2.0	orcarouter	1.6k	262.4k
unsloth/Qwen3.8-27B-unsloth-bnb-4bit	Qwen/Qwen3.8-27B	quantized	-bnb	27.4B	L	apache-2.0	unsloth	19	333.5k
Jackrong/Qwopus3.8-27B-Flash-GGUF	Qwen/Qwen3.8-27B	quantized	GGUF	—	—	apache-2.0	Jackrong	245	289.3k
CodeMasterCody3D/taardis-27b-full-ternary	Qwen/Qwen3.8-27B	quantized	GGUF	—	—	apache-2.0	CodeMasterCody3D	11	270.4k
Maximilian228/Qwen3.8-Flash-Next-NVFP4-GPTQ-Strata	Qwen/Qwen3.8-Flash-Next	quantized	NVFP4	—	—	other	Maximilian228	37	244.9k
agentionai/Qwen3.8-Flash-Next-Gyro-GGUF	Qwen/Qwen3.8-Flash-Next	quantized	GGUF	—	—	other	agentionai	115	229.9k
antirez/qwen3.8-flash-next-gguf	Qwen/Qwen3.8-Flash-Next	quantized	gguf	—	—	other	antirez	14	230.5k
orcarouter/Qwen3.8-27B-Uncensored-NVFP4	Qwen/Qwen3.8-27B	quantized	NVFP4	21.2B	L	apache-2.0	orcarouter	341	199.5k
QUASAR-QAT/Qwen3.8-27B-QUASAR-NVFP4	Qwen/Qwen3.8-27B	quantized	NVFP4	27.8B	L	apache-2.0	QUASAR-QAT	161	177.9k
lued/Qwen3.8-27B-INT8-W8A16-MTP	Qwen/Qwen3.8-27B	quantized	INT8	27.8B	L	apache-2.0	lued	95	180.9k
shawnw3i/Qwen3.8-27B-AWQ-MTP	Qwen/Qwen3.8-27B	quantized	AWQ	6.50B	M	apache-2.0	shawnw3i	11	184.8k
avyukth/Qwen3.8-27B-AWQ-INT4	Qwen/Qwen3.8-27B	quantized	AWQ	27.4B	L	apache-2.0	avyukth	4	176.8k
barrydeen/Qwen3.8-27B-AWQ-4bit	Qwen/Qwen3.8-27B	quantized	AWQ	11.1B	L	apache-2.0	barrydeen	13	167.3k
Bucoid/Qwen3.8-27B-Heretic-Ara-16GB-VRAM-IQ4-XS-MTP-GGUF	Qwen/Qwen3.8-27B	quantized	GGUF	—	—	apache-2.0	Bucoid	91	155.3k
dbirks/Qwen3.8-27B-W4A16-AutoRound	Qwen/Qwen3.8-27B	quantized	-W4A16	6.26B	M	apache-2.0	dbirks	40	154.9k
bartowski/Qwen3.8-Flash-Next-GGUF	Qwen/Qwen3.8-Flash-Next	quantized	GGUF	—	—	other	bartowski	44	154.7k
mlx-community/Qwen3.8-27B-8bit	Qwen/Qwen3.8-27B	quantized	-8bit	27.4B	L	apache-2.0	mlx-community	84	151.4k
amd/Qwen3.8-27B-Quark-AWQ-INT4-W4A16	Qwen/Qwen3.8-27B	quantized	AWQ	6.47B	M	apache-2.0	amd	23	150.8k
Bucoid/Qwen3.8-27B-Uncensored-IQ4-XS-MTP-16GB-VRAM-GGUF	Qwen/Qwen3.8-27B	quantized	GGUF	—	—	apache-2.0	Bucoid	61	147.4k
azukivc/Qwen3.8-27B-Uncensored-GGUF	Qwen/Qwen3.8-27B	quantized	GGUF	—	—	apache-2.0	azukivc	3	147.1k
Pilcothink/Qwen3.8-27B-MixedInt4-AutoRound	Qwen/Qwen3.8-27B	quantized	—	7.01B	M	—	Pilcothink	12	144.9k
local-inference-lab/Qwen3.8-Flash-Next-NVFP4	Qwen/Qwen3.8-Flash-Next	quantized	NVFP4	92.7B	XL	other	local-inference-lab	56	138.2k
incoai/Qwen3.8-27B-DFlash2-GGUF	Qwen/Qwen3.8-27B	quantized	GGUF	—	—	apache-2.0	incoai	169	130k
Cloudflare/clef	Qwen/Qwen3.8-27B	finetune	—	27.4B	L	apache-2.0	Cloudflare	2.3k	24.1k
huihui-ai/Huihui-Qwen3.8-Flash-Next-abliterated-v2-GGUF	Qwen/Qwen3.8-Flash-Next	quantized	GGUF	—	—	other	huihui-ai	122	129.9k
Vishva007/Qwen3.8-27B-W4A16-AutoRound-GPTQ	Qwen/Qwen3.8-27B	quantized	-W4A16	3.03B	M	apache-2.0	Vishva007	11	134.6k
pentacoxian-dev/Qwen3.8-Flash-Next-IQ3E-Q8D-MTP-GGUF	Qwen/Qwen3.8-Flash-Next	quantized	GGUF	—	—	other	pentacoxian-dev	21	130.2k
pearsonkyle/Qwen3.8-27B-GPTQ-W4A16	Qwen/Qwen3.8-27B	quantized	GPTQ	26.9B	L	apache-2.0	pearsonkyle	10	130.7k
Arki05/Qwen3.8-27B-GGUF-shards	Qwen/Qwen3.8-27B	quantized	GGUF	—	—	apache-2.0	Arki05	0	128.7k
orcarouter/Qwen3.8-27B-Uncensored	Qwen/Qwen3.8-27B	finetune	—	27.8B	L	apache-2.0	orcarouter	480	100.7k
Inferact/Qwen3.8-Flash-Next-NVFP4	Qwen/Qwen3.8-Flash-Next	quantized	NVFP4	118B	XXL	other	Inferact	30	120.3k
Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed	Qwen/Qwen3.8-27B	quantized	—	27.4B	L	apache-2.0	Youssofal	166	110.7k
dealignai/Bonsai-2-27B-Ternary-CRACK-GGUF	Qwen/Qwen3.8-27B	quantized	GGUF	—	—	apache-2.0	dealignai	168	110.2k
prism-ml/Ternary-Bonsai-2-27B-mlx-2bit	Qwen/Qwen3.8-27B	finetune	mlx	27.4B	L	apache-2.0	prism-ml	473	91.6k
agentionai/Qwen3.8-Flash-Next-ROCmFP4-FAST-imatrix-GGUF	Qwen/Qwen3.8-Flash-Next	quantized	imatrix	—	—	other	agentionai	88	109.9k
orcarouter/Qwen3.8-Flash-Next-Uncensored-FP8	Qwen/Qwen3.8-Flash-Next	quantized	-FP8	180B	XXL	apache-2.0	orcarouter	57	110.6k
sh0wie/Qwen3.8-Flash-Next-REAP-288-GGUF	Qwen/Qwen3.8-Flash-Next	quantized	GGUF	—	—	other	sh0wie	11	112.7k
lribeiro/Qwen3.8-27B-FP8-Pessoa	Qwen/Qwen3.8-27B	quantized	-FP8	27.8B	L	apache-2.0	lribeiro	4	108.6k
unsloth/Qwen3.8-27B-FP8	Qwen/Qwen3.8-27B	quantized	-FP8	27.8B	L	apache-2.0	unsloth	31	105.9k
SergiioB/Qwen3.8-27B-GPTQ-Int4-sym-G128-MTP-BF16	Qwen/Qwen3.8-27B	quantized	GPTQ	27.8B	L	apache-2.0	SergiioB	27	94.7k
turboderp/Qwen3.8-27B-exl3	Qwen/Qwen3.8-27B	quantized	exl3	—	—	apache-2.0	turboderp	193	85.9k
soyrsoyr/Qwen3.8-27B-W4A16-AWQ-GPTQ	Qwen/Qwen3.8-27B	quantized	-W4A16	11.1B	L	apache-2.0	soyrsoyr	7	93.5k
abhishekchohan/Qwen3.8-27B-GPTQ-INT4-FP8KV	Qwen/Qwen3.8-27B	quantized	GPTQ	27.8B	L	apache-2.0	abhishekchohan	3	92.8k
julianmb/Qwen-3.8-27B-ROCmFP4-FAST-GGUF	Qwen/Qwen3.8-27B	quantized	GGUF	—	—	apache-2.0	julianmb	54	85k
Ar4ikov/Qwen3.8-27B-AWQ-W4A16-ASYM	Qwen/Qwen3.8-27B	quantized	AWQ	27.4B	L	apache-2.0	Ar4ikov	4	82.5k
Freaksterz/Qwen3.8-27B-SmoothQuant-W8A8-INT8	Qwen/Qwen3.8-27B	quantized	-W8A8	21.9B	L	apache-2.0	Freaksterz	25	76.4k
0xKitkat/Qwen3.8-27B-Uncensored-Aggressive	Qwen/Qwen3.8-27B	quantized	GGUF	—	—	apache-2.0	0xKitkat	41	72.9k
ggml-org/Qwen3.8-Flash-Next-GGUF	Qwen/Qwen3.8-Flash-Next	quantized	GGUF	—	—	other	ggml-org	36	72.2k
amd/Qwen3.8-27B-Quark-AWQ-MXFP4	Qwen/Qwen3.8-27B	quantized	AWQ	15.6B	L	apache-2.0	amd	38	71.2k
ivanfioravanti/Qwen3.8-Flash-Next-DS4-Q4	Qwen/Qwen3.8-Flash-Next	quantized	GGUF	—	—	other	ivanfioravanti	16	70.5k
quimmedes/Qwen3.8-27B-XYZ	Qwen/Qwen3.8-27B	quantized	GGUF	—	—	apache-2.0	quimmedes	54	68.5k
nicosuter/Qwen3.8-27B-AWQ	Qwen/Qwen3.8-27B	quantized	AWQ	7.21B	M	apache-2.0	nicosuter	7	70.5k
JonathanColetti/Qwen3.8-27B-Uncensored	Qwen/Qwen3.8-27B	finetune	—	27.4B	L	apache-2.0	JonathanColetti	113	64.8k
Abiray/Qwen3.8-27B-Q4_K_M-GGUF	Qwen/Qwen3.8-27B	quantized	GGUF	—	—	apache-2.0	Abiray	31	68.7k
dealignai/Qwen3.8-27B-UNCENSORED-GGUF	Qwen/Qwen3.8-27B	quantized	GGUF	—	—	apache-2.0	dealignai	74	66.6k
AnonimousA/Qwen3.8-Flash-Next-REAP-256-duo-GGUF	Qwen/Qwen3.8-Flash-Next	quantized	GGUF	—	—	other	AnonimousA	21	68.9k
cometkim/Qwen3.8-27B-nvfp4full-NInfer	Qwen/Qwen3.8-27B	quantized	—	—	—	apache-2.0	cometkim	12	68.9k
Intel/Qwen3.8-Flash-Next-W4A16-AutoRound	Qwen/Qwen3.8-Flash-Next	quantized	-W4A16	75.4B	XL	other	Intel	36	66.8k
agentionai/Qwen3.8-Flash-Next-AP-GGUF	Qwen/Qwen3.8-Flash-Next	quantized	GGUF	—	—	other	agentionai	37	64.5k
pfeifferj/Qwen3.8-Flash-Next-GSQ-RCO-GGUF	Qwen/Qwen3.8-Flash-Next	quantized	GGUF	—	—	other	pfeifferj	51	63.1k
Jundot/Qwen3.8-Flash-Next-oQ4e-mtp	Qwen/Qwen3.8-Flash-Next	quantized	—	180B	XXL	other	Jundot	103	59.9k
mlx-community/Qwen3.8-27B-MTP-4bit	Qwen/Qwen3.8-27B	quantized	-4bit	425M	S	apache-2.0	mlx-community	40	62.7k
huginnfork/Qwen3.8-27B-FP8	Qwen/Qwen3.8-27B	quantized	-FP8	27.8B	L	apache-2.0	huginnfork	40	62.3k
mudler/Qwen3.8-27B-APEX-GGUF	Qwen/Qwen3.8-27B	quantized	GGUF	—	—	apache-2.0	mudler	79	60k
primitive-ai/Qwen3.8-Flash-Next-NVFP4	Qwen/Qwen3.8-Flash-Next	quantized	NVFP4	120B	XXL	other	primitive-ai	25	62.5k
Frozenlock/Qwen3.8-27B-int4-AutoRound	Qwen/Qwen3.8-27B	quantized	int4	6.28B	M	apache-2.0	Frozenlock	26	62.4k
tooltd/Qwen3.8-27B-IQ4-XS-16GB-VRAM-GGUF	Qwen/Qwen3.8-27B	quantized	GGUF	—	—	apache-2.0	tooltd	21	62.5k
RedHatAI/Qwen3.8-27B-NVFP4	Qwen/Qwen3.8-27B	quantized	NVFP4	20.3B	L	apache-2.0	RedHatAI	9	62.9k
kingjones777/Qwen3.8-27B-ROCmFP4-STRIX-MTP-GGUF	Qwen/Qwen3.8-27B	quantized	GGUF	—	—	apache-2.0	kingjones777	39	59.5k
DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU	Qwen/Qwen3.8-27B	finetune	—	27.8B	L	apache-2.0	DavidAU	258	46.4k
sudoingx/Ternary-Bonsai-2-27B-PTQ1_0-MTP-GGUF	Qwen/Qwen3.8-27B	quantized	GGUF	—	—	apache-2.0	sudoingx	72	54k
HemmingwayAI/Hemmingway-1	Qwen/Qwen3.8-27B	finetune	—	26.9B	L	cc-by-nc-4.0	HemmingwayAI	889	13k
kingjones777/Qwen3.8-Flash-Next-Uncensored-ROCmFP4-FAST-GGUF	Qwen/Qwen3.8-Flash-Next	quantized	GGUF	—	—	other	kingjones777	9	56.4k
QQZ2026/Qwen3.8-27B-ZeroRefusal-UD-IQ4_XS-MTP-GGUF	Qwen/Qwen3.8-27B	quantized	GGUF	—	—	apache-2.0	QQZ2026	28	54.7k
ukisai/Swift-Qwen3.8-27b	Qwen/Qwen3.8-27B	finetune	—	27.8B	L	other	ukisai	635	24.3k
aaaljaz/qwen3.8-27b-ninfer-minq4	Qwen/Qwen3.8-27B	finetune	—	—	—	apache-2.0	aaaljaz	2	54.9k
AEON-7/Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-BF16	Qwen/Qwen3.8-27B	finetune	-BF16	27.8B	L	apache-2.0	AEON-7	224	38.5k
PhillyLabs/Qwen3.8-27B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS	Qwen/Qwen3.8-27B	quantized	GGUF	27.4B	L	apache-2.0	PhillyLabs	12	48.8k
Qwen/Qwen3.8-2.4T-A95B-FP8	Qwen/Qwen3.8-2.4T-A95B	quantized	-FP8	2.45T	XXL	other	Qwen	255	36.1k
dealignai/Bonsai-2-27B-1bit-CRACK-GGUF	Qwen/Qwen3.8-27B	quantized	GGUF	—	—	apache-2.0	dealignai	90	44.3k
sh0wie/Qwen3.8-Flash-Next-REAP-288-MLX-4bit	Qwen/Qwen3.8-Flash-Next	quantized	MLX	125B	XXL	other	sh0wie	64	45.5k
ReadyArt/Dark-Scarlett-27B-v2.0	Qwen/Qwen3.8-27B	finetune	—	27.8B	L	apache-2.0	ReadyArt	13	45.6k
btbtyler09/Qwen3.8-27B-GPTQ-4bit	Qwen/Qwen3.8-27B	quantized	GPTQ	27.8B	L	apache-2.0	btbtyler09	10	45.2k
cyankiwi/Qwen3.8-27B-AWQ-BF16-INT4	Qwen/Qwen3.8-27B	quantized	AWQ	27.8B	L	apache-2.0	cyankiwi	18	44.4k
bytkim/Qwen3.8-27B-pi-GGUF	Qwen/Qwen3.8-27B	quantized	GGUF	—	—	apache-2.0	bytkim	53	42.5k
unsloth/Qwen3.8-2.4T-A95B-GGUF	Qwen/Qwen3.8-2.4T-A95B	quantized	GGUF	—	—	other	unsloth	122	38.8k
jcbtc/Qwen3.8-Flash-CIRU-STRIX-IU4	Qwen/Qwen3.8-Flash-Next	quantized	GGUF	—	—	other	jcbtc	41	41.6k
Jundot/Qwen3.8-27B-oQ4e-mtp	Qwen/Qwen3.8-27B	quantized	—	27.8B	L	apache-2.0	Jundot	70	39.6k
Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality	Qwen/Qwen3.8-27B	quantized	—	27.4B	L	apache-2.0	Youssofal	70	39.4k
agentionai/Signal-3.8-Flash-Next-GGUF	Qwen/Qwen3.8-Flash-Next	finetune	GGUF	—	—	other	agentionai	35	40.8k
abihsoro/Qwen3.8-27B-AWQ-INT4	Qwen/Qwen3.8-27B	quantized	AWQ	26.9B	L	apache-2.0	abihsoro	5	40.8k
AnonimousA/Qwen3.8-Flash-Next-REAP-320-GGUF	Qwen/Qwen3.8-Flash-Next	quantized	GGUF	—	—	other	AnonimousA	25	37.6k
ProCreations/Ternary-Bonsai-2-27B-MTP	Qwen/Qwen3.8-27B	quantized	GGUF	—	—	apache-2.0	ProCreations	39	36.6k
Youssofal/Qwen3.8-Flash-Next-MTPLX-Optimized-Speed	Qwen/Qwen3.8-Flash-Next	quantized	—	126B	XXL	other	Youssofal	44	35.9k
jcbtc/Qwen3.8-Flash-CIRU-STRIX-Orca	Qwen/Qwen3.8-Flash-Next	quantized	GGUF	—	—	other	jcbtc	40	36.1k
agentionai/Signal-3.8-27B-GGUF	Qwen/Qwen3.8-27B	finetune	GGUF	—	—	apache-2.0	agentionai	103	32.8k
Ryn1998/Qwen3.8-27B-Heretic-Abliterated-Uncensored-GGUF	Qwen/Qwen3.8-27B	quantized	GGUF	—	—	apache-2.0	Ryn1998	20	36k
Comfy-Org/Qwen3.8-27B	Qwen/Qwen3.8-27B	finetune	—	—	—	apache-2.0	Comfy-Org	25	35.6k

Get alerts on the Qwen3.8 family

Watch this family

/feeds/families/Qwen--Qwen3.8.xml(RSS 2.0) · every change to any Qwen3.8 member

Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.