Get

Name: OpenWeights Terminal measured pairs
Creator: Dvidia
License: https://owterminal.com/cite

Only exact hub artifacts. If the capture did not name a file, the row stays unlinked.

Model · Build	Hardware	Decode · tok/s	Get
Qwen3.6-35B-A3B4bit	M4 Pro	85.5	HF
Qwen3.8-27BUD-Q4_K_XL	RTX 4090 24GB	40.7	HF
Ornith	GTX 1660 SUPER 6GB	40	HF
Qwen3.8-27BIQ3_XXS	RTX 5060 Ti 16GB	23	HF
Qwen3.8-27BUD-Q2_K_XL	RTX 5060 Ti 16GB	19	HF
Qwen3.8-Flash-NextNVFP4	RTX 5090 32GB	80.9	Bench
MiMo-V2.6-Distill-Qwen-9BQ5_K_M	RTX 5060 8GB	47	MiMo
AliceAI-Foundation-80B-A3BQ4_K_M	M5 Max 128GB	65	HF
Qwen3.8-27BNVFP4	DGX Spark	72	Get
GLM 5.3 FlashEXL3	2× DGX Spark	60.4	Recipe
GLM 5.3 FlashEXL3	DGX Spark	18.6	Get
Qwen3.8-Flash-Next~2.6 bits	M5 Pro 64GB	41.4	HF
Qwen3.8-Flash-Next CoderIQ1_M	RTX 5060 Ti 16GB + RTX 3070 8GB	127	Strata
Ternary Bonsai 2 27Bternary	RTX 3060 12GB	50	HF GGUF
Ternary Bonsai 2 27BPTQ1_0	RTX 5060 Ti 16GB	54.7	HF GGUF
Qwen3.8-Flash-NextUD-Q4_K_XL	RTX 5090	114.3	llama.cpp
Qwen3.8-Flash-NextIQ2_XS	RTX 3080 Ti 12GB	79	Strata
Qwen3.8-Flash-NextIQ3_S	RTX 3090 24GB	70	Strata
Qwen3.8-Flash-NextIQ2_XS	RTX 3090 24GB	87	Strata
Qwen3.8-Flash-NextIQ3_S	2× RTX 3090 24GB	158.3	Strata
Qwen3.8-Flash-NextIQ3_S	2× RTX 3090 24GB	153.4	Strata
Qwen3.8-Flash-NextIQ3_S	RTX 5090	195.8	Strata
Qwen3.8-Flash-NextIQ3_S	RTX 3090 24GB	100	Strata
UUnderdog Saluki 27B2-bit	DGX Spark	53	Spark recipe
Qwen3.8-Flash-NextQ2_0	RTX 5090	191	Strata
Qwen3.8-Flash-NextIQ3_S	RTX 5080 16GB	50	Strata
GLM 5.3 FlashEXL3	4× RTX PRO 6000	264	Mia recipe
GLM 5.3 FlashEXL3	2× RTX PRO 6000	238	Aevonix recipe
Swift 1.5 Qwen3.8 Flash-NextIQ2_XS	RTX 4090 24GB	220	Strata
Qwen3.8-Flash-NextIQ2_XS	RTX 3060 12GB	27.7	Strata
Qwen3.8-Flash-NextIQ3_S	RTX 3090 24GB	72	Strata
Qwen3.6-35B-A3BUD-IQ3_XXS	M1 Max 32GB	37	HF
Qwen3.8-27B4-bit	DGX Spark	102.9	HF
Qwen3.8-27B4-bit	M5 Pro 64GB	89.9	HF
Qwen3.8-27B4-bit	M6 mini 32GB	61.9	HF
Qwen3.8-Flash-NextIQ3_S	RTX 5090 32GB	104	Strata
Qwen3.8-Flash-NextNVFP4	DGX Spark	74.8	TensorFold
Qwen3.8-Flash-NextIQ3_S	RTX 5090 32GB	142	Strata
Qwen3.8-27BNVFP4	RTX A5000	177.6	TensorFold
GLM 5.3 FlashNVFP4	2x DGX Spark	55.6	Recipe
Qwen3.8-Flash-NextIQ2_XS	RTX 3090 24GB	100.6	Strata
Qwen3.8-Flash-NextIQ3_S	RTX 3080 10GB	52.7	Strata
Qwen3.8-Flash-NextIQ3_S	RTX 4060 Ti	50	Strata
Qwen3.8-Flash-NextIQ3_S	2× RTX 5060 Ti 16GB	99.9	Strata
Qwen3.8-Flash-NextIQ3_XXS	RTX 5070 12GB	66.7	Strata
Qwen3.8-Flash-NextIQ3_S	RTX 5070 Ti 16GB	53.5	Strata
Qwen3.8-Flash-NextIQ3_S	2× RTX 3060 12GB	40	Strata
Qwen3.8-Flash-NextUD-IQ4_XS	Ryzen AI Max+ 395 128GB	53.8	v0.1.40
GLM 5.3EXL3 3.0bpw	4x DGX Spark	38.4	RigMark
GLM 5.3 FlashEXL3 2.05bpw	DGX Spark	32.3	EXL3
GLM 5.3NVFP4	8× DGX Spark	40	NVFP4
DeepSeek v4.1 Flash2.70 bpw	2× DGX Spark	103	vLLM recipe
Qwen3.8-Flash-NextQ4_K_XL-DN4	4× Tesla V100 32GB	60	Strata
Qwen3.8-Flash-NextIQ3_S	RTX 4060 Ti 16GB	55	Strata
Qwen3.8-Flash-NextQ2_0	Intel Arc B570 10GB	9.0	Strata
Gemma-4 26B-A4B-itUD-Q4_K_XL	Radeon RX 9060 XT 16GB	88	llama.cpp
Qwen3.8-Flash-NextIQ3_S	RTX 3090 + RTX 2070 SUPER	34.2	Strata
Qwen3.8-Flash-NextIQ3_S	RTX 4060 Ti 16GB	55	Strata
Qwen3.8-27BIQ4_XS	RTX 5090	186	llama.cpp
Nemotron 3.5 Bolt 74B2-bit	DGX Spark	80	HF
Qwen3.8-Flash-NextFP4	DGX Spark	65	HF FP4-Local
DeepSeek v4.1 Flashunspecified	2× DGX Spark	93.6	GitHub
Qwen3.8-Flash-NextUD-IQ4_XS	RTX 4090	92	Strata
Qwen3.8-Flash-Nextunspecified	RTX 5090	42.1	crow-nest
Qwen3.5 2BQ4_K_M	RTX 5090 32GB	351	unlinked
Gemma-4 26B-A4B-itQ4_K_M	RTX 5090 32GB	173	unlinked
Qwen3.8-Flash-Next	M5 Max	126.5	unlinked
Qwen3.6-35B-A3BNVFP4	2× DGX Spark	94.4	unlinked
Qwen3.5-4B4bit	M4 Pro	82.8	unlinked
Qwen3.5-9B4bit	M4 Pro	49.3	unlinked
Qwen3-8B4bit	M4 Pro	48.3	unlinked
Empero Qwen3.8-35B-A3BQ4_K_M	RTX 3060 12GB	50	unlinked
Qwen3.8-Flash-NextFP8	2× DGX Spark	45	unlinked
Nex-N2.5-miniQ4_K_M	RTX 5060 Ti 16GB	14	unlinked
Qwen3.8-27B TurboFCFusionIQ2_M	RTX 5060 Ti 16GB	10	unlinked
Qwen3.8-Flash-NextEXL3	DGX Spark	79.5	unlinked
GLM 5.3 FlashEXL3 4bpw	4× DGX Spark	104	unlinked
GLM 5.3 Flashunknown	4× DGX Spark	127	unlinked
RRED-SNOW 5.3 Flash2.49 bpw	DGX Spark	33.0	unlinked
CYBER-FROST 3.83.87 bpw	DGX Spark	54.7	unlinked
GLM 5.3NVFP4	4× DGX Spark	35	unlinked
Qwen3.8-Flash-Next4-bit QAD	DGX Spark	65	unlinked
Qwen3.8-Flash-NextFP8	2× DGX Spark	58	unlinked
Qwen3.8-Flash-NextNVFP4	DGX Spark	32	unlinked
Qwen3.8-Flash-Next4bit	DGX Spark	50.2	unlinked
Qwen3.8-Flash-NextIQ3_S	2× AMD MI50 32GB	52	unlinked
Qwen3.8-Flash-NextIQ3_S	AMD MI50 32GB	26.8	unlinked
Qwen3.8-Flash-NextQ4_XL	RTX PRO 6000	92.8	unlinked
DeepSeek v4.1 FlashQ2	RTX PRO 6000	57.7	unlinked
Qwen3.8-Flash-NextQ4_K_M	M5 Max 64GB	7.8	unlinked
Qwen3.8-27BNVFP4	DGX Spark	42.3	unlinked
Qwen3.8-27BNVFP4	DGX Spark	28.7	unlinked
Qwen3.8-27BNVFP4	DGX Spark	31.8	unlinked
Qwen3.6-35B-A3B4-bit	M4 Pro 64GB	108.6	unlinked
Qwen3.8-27BNVFP4	RTX PRO 6000 Blackwell Max-Q	272.8	unlinked
Qwen3.8-27BNVFP4	RTX PRO 6000 Blackwell Max-Q	151.4	unlinked
GLM 5.3 FlashNVFP4	2x DGX Spark	15	unlinked
Qwen3.8-27BNVFP4	RTX A5000	139.3	unlinked
GLM 5.3Int4/Int8	4x DGX Spark	30	unlinked
GLM 5.3 FlashEXL3 4bpw	RTX PRO 6000 + 2× GB10	120	unlinked
GLM 5.3 FlashEXL3	2x DGX Spark	85	unlinked
Qwen3.8-Flash-Next CoderGSQ-RCO	M5 Max 64GB	51	unlinked
Qwen3.8-Flash-NextIQ3_S	2× RTX 3090 24GB	122.5	unlinked
GLM 5.3 FlashEXL3 2.05bpw	DGX Spark	30	unlinked
REAP50 GLM 5.3 FlashQ2	Radeon RX 9070 XT	10	unlinked
GLM 5.3NVFP4	2× DGX Station GB300	81.5	unlinked
Qwen3.8-Flash-NextUD-IQ4_XS	Tesla V100 32GB	57	unlinked
GLM 5.3 FlashQ2	Mac Studio M4 Max 64GB	11.3	unlinked
Qwen3.8-Flash-NextQ2_0	Intel Arc B570 10GB	32.4	unlinked
Qwen3.8-27B4bit	RTX 5090	370	unlinked
Qwen3.8-27BEXL3	RTX 5090	258	unlinked