58 ranked

Took the throneQwen3.5 2Bvs Sep 15Aug · Qwen3.6-35B-A3B · heldSep · Qwen3.5 2BNations

Liberated

#	Model · Build	Hardware			Runtime	Proof
1NEW	Qwen3.5 2BQ4_K_M RTX 5090	RTX 5090	351	—	—	@fillagrew
2NEW	Qwen3.8-27BNVFP4 RTX PRO 6000 Blackwell Max-Q	RTX PRO 6000 Blackwell Max-Q	272.8	—	TensorFold	@llm_frontier_jp
3NEW	GLM 5.3 FlashEXL3 4× RTX PRO 6000	4× RTX PRO 6000	264	—	TensorFold 0.6.2	@Kurcide
4NEW	GLM 5.3 FlashEXL3 2× RTX PRO 6000	2× RTX PRO 6000	238	—	TensorFold 0.6.5	@Kurcide
5NEW	Swift 1.5 Qwen3.8 Flash-NextIQ2_XS RTX 4090	RTX 4090	220	3830	Strata	@Knuckles_XBT
6NEW	Qwen3.8-27BNVFP4 RTX A5000	RTX A5000	177.6	—	TensorFold	@Ja6ek
7NEW	Gemma-4 26B-A4B-itQ4_K_M RTX 5090	RTX 5090	173	—	—	@fillagrew
8NEW	Qwen3.8-27BNVFP4 RTX PRO 6000 Blackwell Max-Q	RTX PRO 6000 Blackwell Max-Q	151.4	—	vLLM	@llm_frontier_jp
9NEW	Qwen3.8-Flash-NextIQ3_S RTX 5090	RTX 5090	142	—	Strata	@arianpg
10NEW	Qwen3.8-27BNVFP4 RTX A5000	RTX A5000	139.3	—	vLLM	@Ja6ek
11NEW	Qwen3.8-Flash-Next M5 Max	M5 Max	126.5	—	MTPLX V2.11.3	@Youssofal_
12NEW	GLM 5.3 FlashEXL3 4bpw RTX PRO 6000 + 2× GB10	RTX PRO 6000 + 2× GB10	120	—	TensorFold	@hokazuya
13▼12	Qwen3.6-35B-A3B4-bit M4 Pro 64GB	M4 Pro 64GB	108.6	—	Rapid-MLX	@draslan_eth
14NEW	Qwen3.8-Flash-NextIQ3_S RTX 5090	RTX 5090	104	1657	Strata	@DaSun64125381
15NEW	Qwen3.8-27B4-bit DGX Spark	DGX Spark	102.9	—	TensorFold	@Oluwaphilemon1
16NEW	Qwen3.8-Flash-NextIQ2_XS RTX 3090 24GB	RTX 3090 24GB	100.6	—	Strata	@draslan_eth
17NEW	Qwen3.8-Flash-NextIQ3_S 2× RTX 5060 Ti 16GB	2× RTX 5060 Ti 16GB	99.9	—	Strata	@needmorevram
18▼16	Qwen3.6-35B-A3BNVFP4 DGX Spark	DGX Spark	94.4	181.5	—	@bonellisystems
19NEW	Qwen3.8-Flash-NextQ4_XL RTX PRO 6000	RTX PRO 6000	92.8	—	llama.cpp b11412	@piyo621
20NEW	Qwen3.8-27B4-bit M5 Pro 64GB	M5 Pro 64GB	89.9	—	TensorFold	@aartiles24
21▼18	Qwen3.6-35B-A3B4bit M4 Pro	M4 Pro	85.5	—	rapid-mlx	@rapidmlx
22NEW	GLM 5.3 FlashEXL3 DGX Spark	DGX Spark	85	—	TensorFold	@MehdiHacks
23NEW	Qwen3.5-4B4bit M4 Pro	M4 Pro	82.8	—	rapid-mlx	@rapidmlx
24NEW	Qwen3.8-Flash-NextNVFP4 RTX 5090	RTX 5090	80.9	—	—	@tekizaihq
25NEW	Qwen3.8-Flash-NextEXL3 DGX Spark	DGX Spark	79.5	—	EXL3	@yume_arasaki
26NEW	Qwen3.8-Flash-NextNVFP4 DGX Spark	DGX Spark	74.8	—	TensorFold	@redp314
27NEW	Qwen3.8-27BNVFP4 DGX Spark	DGX Spark	72	—	—	@hasso5703
28NEW	Qwen3.8-Flash-NextIQ3_S RTX 3090 24GB	RTX 3090 24GB	72	—	Strata	@needmorevram
29NEW	Qwen3.8-Flash-NextIQ3_XXS RTX 5070 12GB	RTX 5070 12GB	66.7	—	Strata	@jun1228909
30NEW	AliceAI-Foundation-80B-A3BQ4_K_M M5 Max	M5 Max	65	—	llama.cpp	@aqty
31NEW	Qwen3.8-27B4-bit M6 mini 32GB	M6 mini 32GB	61.9	—	TensorFold	@jmurillocode
32NEW	GLM 5.3 FlashEXL3 DGX Spark	DGX Spark	60.4	1950	TensorFold	@MiaAI_lab
33NEW	DeepSeek v4.1 FlashQ2 RTX PRO 6000	RTX PRO 6000	57.7	—	llama.cpp b11412	@piyo621
34NEW	GLM 5.3 FlashNVFP4 DGX Spark	DGX Spark	55.6	—	—	@PlusTen_AI
35NEW	Qwen3.8-Flash-NextIQ3_S RTX 5070 Ti 16GB	RTX 5070 Ti 16GB	53.5	—	Strata	@raminaol9ykas
36NEW	Qwen3.8-Flash-NextIQ3_S RTX 3080 10GB	RTX 3080 10GB	52.7	—	Strata	@needmorevram
37NEW	Empero Qwen3.8-35B-A3BQ4_K_M RTX 3060	RTX 3060	50	550	llama.cpp	@Oluwaphilemon1
38NEW	Qwen3.8-Flash-NextIQ3_S RTX 4060 Ti	RTX 4060 Ti	50	—	Strata	@xiaobei1943
39NEW	Qwen3.5-9B4bit M4 Pro	M4 Pro	49.3	—	rapid-mlx	@rapidmlx
40▼36	Qwen3-8B4bit M4 Pro	M4 Pro	48.3	—	rapid-mlx	@rapidmlx
41NEW	MiMo-V2.6-Distill-Qwen-9BQ5_K_M RTX 5060	RTX 5060	47	1600	llama.cpp	@stfu0911
42NEW	Qwen3.8-Flash-NextFP8 DGX Spark	DGX Spark	45	—	—	@Oluwaphilemon1
43NEW	Qwen3.8-27BNVFP4 DGX Spark	DGX Spark	42.3	—	TensorFold 0.6.3	@edurdias
44NEW	Qwen3.8-27BUD-Q4_K_XL RTX 4090	RTX 4090	40.7	2659.8	llama.cpp	@Oluwaphilemon1
45NEW	Ornith GTX 1660 SUPER	GTX 1660 SUPER	40	—	—	@mine_craft_bui
46NEW	Qwen3.8-Flash-NextIQ3_S 2× RTX 3060 12GB	2× RTX 3060 12GB	40	—	Strata	@xr_ymchn
47▼42	Qwen3.6-35B-A3BUD-IQ3_XXS M1 Max 32GB	M1 Max 32GB	37	350	—	@moonsteroid
48NEW	Qwen3.8-27BNVFP4 DGX Spark	DGX Spark	31.8	—	SGLang 0.5.21	@edurdias
49NEW	GLM 5.3Int4/Int8 DGX Spark	DGX Spark	30	840	sparkDash	@majewskizby
50NEW	Qwen3.8-27BNVFP4 DGX Spark	DGX Spark	28.7	—	vLLM 0.30.0	@edurdias
51NEW	Qwen3.8-Flash-NextIQ2_XS RTX 3060	RTX 3060	27.7	—	Strata	@dec21ai
52NEW	Qwen3.8-27BIQ3_XXS RTX 5060 Ti	RTX 5060 Ti	23	—	llama.cpp	@fntAInhead
53NEW	Qwen3.8-27BUD-Q2_K_XL RTX 5060 Ti	RTX 5060 Ti	19	—	llama.cpp	@fntAInhead
54NEW	GLM 5.3 FlashEXL3 DGX Spark	DGX Spark	18.6	—	EXL3	@vcruz305
55NEW	GLM 5.3 FlashNVFP4 DGX Spark	DGX Spark	15	—	vLLM	@sudoingX
56NEW	Nex-N2.5-miniQ4_K_M RTX 5060 Ti	RTX 5060 Ti	14	—	llama.cpp	@fntAInhead
57NEW	Qwen3.8-27B TurboFCFusionIQ2_M RTX 5060 Ti	RTX 5060 Ti	10	—	llama.cpp	@fntAInhead
58NEW	Qwen3.8-Flash-NextQ4_K_M M5 Max	M5 Max	7.8	—	LM Studio	@miya_mos365

Qwen3.8-Flash-Next

2× GeForce RTX 3060 12GB

2× RTX 3060 12GB · Strata · IQ3_S GGUF

Pair

#46 / 58 in this filter

#1 / 1 on this chip

#16 / 18 of this model

Decode · tok/s

Prefill

Peak

This model elsewhere

Lineage

Officialclaimed

Originating sentence

短コンテキストだと 40 tok/s、50k 超の長コンテキストで 10% 程度減速するけどほぼ誤差の範囲。モデルは公式版の IQ3_S

Flags

official IQ3_S · short context · 54.3 GB RAM · DDR4-3200 · i3-14100F

Caveat

First-person 2× 3060 12GB. Rank is the quoted 40 short-context decode. Prefill was not in this post.

Proof

@xr_ymchn

Get

Get on Strata

Pairs

Liberated