LongCat Flash Lite

Meituan · meituan/longcat-flash-lite

Provider	Meituan
Family	longcat
Type	llm-chat
Status	active
Released	2026-01-27
Updated	2026-02-06
Parameters	69.1B
Open weights	yes

What it fits on

Ordered by predicted speed. Bandwidth sets decode rate; memory decides whether it runs at all.

Every figure here is computed, not measured. Fit is weights at each quantisation against device memory, with a 25% allowance for the KV cache, activations and the OS. Decode rate is the memory-bandwidth roofline at 70% efficiency. Nobody has run this model on these devices. This is a mixture-of-experts model and no card carries active-parameter counts, so these predictions use total parameters and understate the real speed.

Device	Memory	Bandwidth	Best quality	Weights	tok/s	Fastest
NVIDIA GB200 Grace Blackwell Superchip	372.0 GB	16000.0 GB/s	bf16	138.15 GB	~81.1	~324.3 q4
AMD Instinct MI355X	288.0 GB	8000.0 GB/s	bf16	138.15 GB	~40.5	~162.1 q4
NVIDIA B200	180.0 GB	7700.0 GB/s	fp8	69.07 GB	~78.0	~156.1 q4
Google TPU7x (Ironwood)	192.0 GB	7380.0 GB/s	bf16	138.15 GB	~37.4	~149.6 q4
AMD Instinct MI325X	256.0 GB	6000.0 GB/s	bf16	138.15 GB	~30.4	~121.6 q4
AMD Instinct MI300X	192.0 GB	5300.0 GB/s	bf16	138.15 GB	~26.9	~107.4 q4
NVIDIA H200 SXM	141.0 GB	4800.0 GB/s	fp8	69.07 GB	~48.6	~97.3 q4
NVIDIA H100 NVL	94.0 GB	3900.0 GB/s	fp8	69.07 GB	~39.5	~79.0 q4
NVIDIA H100 SXM	80.0 GB	3350.0 GB/s	q6	51.81 GB	~45.3	~67.9 q4
AMD Instinct MI250X	128.0 GB	3200.0 GB/s	fp8	69.07 GB	~32.4	~64.9 q4
Google TPU v5p	95.0 GB	2765.0 GB/s	fp8	69.07 GB	~28.0	~56.0 q4
NVIDIA A100 80GB SXM	80.0 GB	2039.0 GB/s	q6	51.81 GB	~27.6	~41.3 q4
NVIDIA H100 PCIe	80.0 GB	2000.0 GB/s	q6	51.81 GB	~27.0	~40.5 q4
AMD Instinct MI210	64.0 GB	1600.0 GB/s	q5	43.17 GB	~25.9	~32.4 q4
NVIDIA L40S	48.0 GB	864.0 GB/s	q4	34.54 GB	~17.5	~17.5 q4
Apple M3 Ultra	512.0 GB	819.0 GB/s	bf16	138.15 GB	~4.1	~16.6 q4
Apple M2 Ultra	192.0 GB	800.0 GB/s	bf16	138.15 GB	~4.1	~16.2 q4
Apple M4 Max	128.0 GB	546.0 GB/s	fp8	69.07 GB	~5.5	~11.1 q4
Apple M1 Max	64.0 GB	400.0 GB/s	q5	43.17 GB	~6.5	~8.1 q4
Apple M2 Max	96.0 GB	400.0 GB/s	fp8	69.07 GB	~4.1	~8.1 q4
Apple M3 Max	128.0 GB	400.0 GB/s	fp8	69.07 GB	~4.1	~8.1 q4
Apple M4 Pro	64.0 GB	273.0 GB/s	q5	43.17 GB	~4.4	~5.5 q4

Where it runs

Taken from the card's availability section.

Platform	Id on that platform
Hugging Face	meituan-longcat/LongCat-Flash-Lite

Verified benchmark evidence

Each row was checked against its source by a reviewer, and carries the model identifier as actually evaluated — which is not always the same as this card's.

Benchmark	Evaluated as	Score	Evidence date	Source kind
aa_lcr	LongCat Flash Lite	28.33%	2026-09-10 evaluated	independent evaluator	source
critpt	LongCat Flash Lite	0.0%	2026-09-10 evaluated	independent evaluator	source
gpqa_diamond	LongCat Flash Lite	63.64%	2026-09-10 evaluated	independent evaluator	source

Reported benchmark scores

This card reports no benchmark scores yet.

Benchmark	Catalogue standing	Score

Data

This card as JSON · See it in the graph · Edit on GitHub