qwen35b-a3b-fable-sft-abliterated — which GPUs fit

hotdogs · 34.7B (active 3.0B) · MoE · ctx 32K · agpl-3.0 · HuggingFace

qwen35b-a3b-fable-sft-abliterated (hotdogs) is a 34.7B parameters MoE (3.0B active per token) open-weight model tracked on AI Hashrate. At 8K context we estimate roughly 20.69 GB VRAM for Q4 (weights 19.09 GB + KV 0.6 GB + 1 GB overhead) and 71.0 GB for FP16. About 28 GPUs/accelerators in our catalog fully fit this model at Q4 under that context assumption. Fastest Q4 configs: B200 192GB SXM ≈ 1697.0 tok/s (estimated); MI300X 192GB ≈ 1124.2 tok/s (estimated); H200 141GB SXM5 ≈ 1018.2 tok/s (estimated); H100 80GB SXM5 ≈ 710.6 tok/s (estimated); Gaudi 3 128GB ≈ 694.9 tok/s (estimated). Use the table below for VRAM fit and tok/s per dollar (list MSRP). Estimates follow memory-bandwidth math; measured rows override when present. See methodology for details. Methodology.

90 hardware configs — sorted by tok/s. Default fit context 8K.

Hardware	VRAM	Quant	tok/s	Fits?	tok/s/$
B200 192GB SXM	192	Q4	1697.0 est.	Yes	0.042
MI300X 192GB	192	Q4	1124.2 est.	Yes	0.075
H200 141GB SXM5	141	Q4	1018.2 est.	Yes	0.029
H100 80GB SXM5	80	Q4	710.6 est.	Yes	0.024
Gaudi 3 128GB	128	Q4	694.9 est.	Yes	0.056
B200 192GB SXM	192	FP16	466.7 est.	Yes	0.012
RX 7900 XT 20GB	20	Q4	451.9 est.	No	0.503
A100 80GB SXM4	80	Q4	432.5 est.	Yes	0.029
RTX 5090 32GB	32	Q4	380.1 est.	Yes	0.19
RTX 5080 16GB	16	Q4	346.9 est.	No	0.347
RTX 5070 Ti 16GB	16	Q4	323.7 est.	No	0.432
MI300X 192GB	192	FP16	309.2 est.	Yes	0.021
H200 141GB SXM5	141	FP16	280.0 est.	Yes	0.008
RTX 4080 Super 16GB	16	Q4	265.9 est.	No	0.266
RTX 4070 Ti Super 16GB	16	Q4	242.8 est.	No	0.304
RX 9070 16GB	16	Q4	231.2 est.	No	0.421
RX 9070 XT 16GB	16	Q4	231.2 est.	No	0.386
RX 7800 XT 16GB	16	Q4	225.5 est.	No	0.452
RTX 4090 24GB	24	Q4	213.8 est.	Yes	0.134
RTX 4090D 24GB (China)	24	Q4	213.8 est.	Yes	0.134
RTX 3090 Ti 24GB	24	Q4	213.8 est.	Yes	0.107
RX 7900 GRE 16GB	16	Q4	208.1 est.	No	0.379
RX 7900 XTX 24GB	24	Q4	203.6 est.	Yes	0.204
RTX 6000 Ada 48GB	48	Q4	203.6 est.	Yes	0.03
Arc A770 16GB	16	Q4	202.3 est.	No	0.58
RTX 3090 24GB	24	Q4	198.5 est.	Yes	0.132
H100 80GB SXM5	80	FP16	195.4 est.	Yes	0.007
Gaudi 3 128GB	128	FP16	191.1 est.	Yes	0.015
L40S 48GB	48	Q4	183.3 est.	Yes	0.023
Mac Studio M3 Ultra 96GB	96	Q4	173.7 est.	Yes	0.043
Mac Studio M2 Ultra 192GB	192	Q4	169.7 est.	Yes	0.024
RTX A6000 48GB	48	Q4	162.9 est.	Yes	0.036
RTX 5060 Ti 16GB	16	Q4	161.9 est.	No	0.377
RTX 5070 12GB	12	Q4	136.4 est.	No	0.248
Titan V 12GB	12	Q4	132.5 est.	No	0.044
Arc Pro B70 32GB	32	Q4	129.0 est.	Yes	0.129
A100 80GB SXM4	80	FP16	118.9 est.	Yes	0.008
MacBook Pro M4 Max 128GB	128	Q4	115.8 est.	Yes	0.026
T4 16GB	16	Q4	115.6 est.	No	0.058
RTX 4070 Ti 12GB	12	Q4	112.5 est.	No	0.141
Titan Xp 12GB	12	Q4	111.3 est.	No	0.093
RTX 3080 10GB	10	Q4	107.1 est.	No	0.153
DGX Spark (GH200 480GB)	480	Q4	106.1 est.	Yes	0.035
RTX 4060 Ti 16GB	16	Q4	104.1 est.	No	0.209
RX 7600 XT 16GB	16	Q4	104.1 est.	No	0.316
RTX 4070 12GB	12	Q4	102.3 est.	No	0.171
RTX 4070 Super 12GB	12	Q4	102.3 est.	No	0.171
Titan X Pascal 12GB	12	Q4	97.5 est.	No	0.081
Arc B580 12GB	12	Q4	92.6 est.	No	0.372
RX 7700 XT 12GB	12	Q4	87.7 est.	No	0.195
MacBook Pro M1 Max 32GB	32	Q4	84.8 est.	Yes	0.026
MacBook Pro M1 Max 64GB	64	Q4	84.8 est.	Yes	0.022
MacBook Pro M3 Max 128GB	128	Q4	84.8 est.	Yes	0.02
RTX 3060 12GB	12	Q4	73.1 est.	No	0.222
RTX 6000 Ada 48GB	48	FP16	73.1 est.	No	0.011
L40S 48GB	48	FP16	65.7 est.	No	0.008
RTX 5090 32GB	32	FP16	60.6 est.	No	0.03
RTX A6000 48GB	48	FP16	58.4 est.	No	0.013
Mac mini M4 Pro 64GB	64	Q4	57.9 est.	Yes	0.026
MacBook Pro M1 Max 64GB	64	FP16	54.1 est.	No	0.014
Arc B570 10GB	10	Q4	53.5 est.	No	0.244
Mac Studio M3 Ultra 96GB	96	FP16	47.8 est.	Yes	0.012
Mac Studio M2 Ultra 192GB	192	FP16	46.7 est.	Yes	0.007
Ryzen AI Max+ 395 128GB	96	Q4	45.6 est.	Yes	0.023
Ryzen AI Max+ 395 64GB	48	Q4	45.6 est.	Yes	0.03
Ryzen AI Max 390 64GB	48	Q4	45.6 est.	Yes	0.035
RTX 5060 8GB	8	Q4	40.3 est.	No	0.135
RTX 5060 Ti 8GB	8	Q4	40.3 est.	No	0.106
RTX 3070 8GB	8	Q4	40.3 est.	No	0.081
Mac mini M4 Pro 64GB	64	FP16	36.9 est.	No	0.017
MacBook Pro M4 Max 128GB	128	FP16	31.8 est.	Yes	0.007
DGX Spark (GH200 480GB)	480	FP16	29.2 est.	Yes	0.01
RTX 4060 Ti 8GB	8	Q4	25.9 est.	No	0.065
RX 7600 8GB	8	Q4	25.9 est.	No	0.096
Mac mini M4 32GB	32	Q4	25.5 est.	Yes	0.026
RTX 4060 8GB	8	Q4	24.5 est.	No	0.082
MacBook Pro M3 Max 128GB	128	FP16	23.3 est.	Yes	0.006
Arc Pro B70 32GB	32	FP16	20.6 est.	No	0.021
RTX 4090 24GB	24	FP16	19.2 est.	No	0.012
RTX 4090D 24GB (China)	24	FP16	19.2 est.	No	0.012
RTX 3090 Ti 24GB	24	FP16	19.2 est.	No	0.01
RX 7900 XTX 24GB	24	FP16	18.2 est.	No	0.018
RTX 3090 24GB	24	FP16	17.8 est.	No	0.012
Tesla P4 8GB	8	Q4	17.3 est.	No	0.216
Ryzen AI Max+ 395 64GB	48	FP16	16.4 est.	No	0.011
Ryzen AI Max 390 64GB	48	FP16	16.4 est.	No	0.013
MacBook Pro M1 Max 32GB	32	FP16	13.5 est.	No	0.004
Ryzen AI Max+ 395 128GB	96	FP16	12.5 est.	Yes	0.006
RX 7900 XT 20GB	20	FP16	10.6 est.	No	0.012
Mac mini M4 32GB	32	FP16	4.1 est.	No	0.004

Fit checks

RTX 5090 32GB — fits · ≈380.1 tok/s Q4 est.
RTX 3090 Ti 24GB — fits · ≈213.8 tok/s Q4 est.
RTX 4090 24GB — fits · ≈213.8 tok/s Q4 est.
RTX 5080 16GB — does not fit · ≈346.9 tok/s Q4 est.
RTX 6000 Ada 48GB — fits · ≈203.6 tok/s Q4 est.
RX 7900 XTX 24GB — fits · ≈203.6 tok/s Q4 est.
RTX 3090 24GB — fits · ≈198.5 tok/s Q4 est.
RTX 5070 Ti 16GB — does not fit · ≈323.7 tok/s Q4 est.
L40S 48GB — fits · ≈183.3 tok/s Q4 est.
Mac Studio M3 Ultra 96GB — fits · ≈173.7 tok/s Q4 est.
Mac Studio M2 Ultra 192GB — fits · ≈169.7 tok/s Q4 est.
RX 7900 XT 20GB — does not fit · ≈451.9 tok/s Q4 est.

12 popular retail GPUs; every row in the table above also links its Fits? verdict to the full fit check.