Open-weight models that run on NVIDIA RTX 6000 Ada Generation

Memory 48 GB
Bandwidth 960 GB/s
FP16 dense 364.2 TFLOPS
Usable 43.2 GB

Specs: Memory · NVIDIA RTX 6000 Ada Generation | NVIDIA (datasheet) · Bandwidth · NVIDIA RTX 6000 Ada Generation | NVIDIA (datasheet) · FP16 dense · NVIDIA Ada Lovelace Professional GPU Architecture (whitepaper V1.1)

Search Precision Context Concurrent requests Minimum speed Architecture Type Maker Sort

Fit	Model	Parameters / active	Precision	Memory	Est. speed	Longest context	Runs as
Runs well	Qwen3-Next-80B-A3B-Instruct Alibaba Qwen	81.3B / 3B	IQ4_XS	42.4 / 43.2 GB	267–401 tok/s	40K	One GPU
Runs well	Qwen3-Next-80B-A3B-Thinking Alibaba Qwen	81.3B / 3B	IQ4_XS	42.4 / 43.2 GB	267–401 tok/s	40K	One GPU
Runs well	Qwen3-Coder-Next Alibaba Qwen	79.7B / 3B	IQ4_XS	41.6 / 43.2 GB	267–401 tok/s	77K	One GPU
Runs well	Qwen3.5-35B-A3B Alibaba Qwen	36B / 3B	Q8_0	37.5 / 43.2 GB	143–215 tok/s	256K	One GPU
Runs well	Qwen3.6-35B-A3B Alibaba Qwen	36B / 3B	Q8_0	37.5 / 43.2 GB	143–215 tok/s	256K	One GPU
Runs well	Qwen2.5-VL-32B-Instruct Alibaba Qwen	33.5B	Q8_0	36.8 / 43.2 GB	13–19 tok/s	33K	One GPU
Runs well	Qwen3-VL-32B-Instruct Alibaba Qwen	33.4B	Q8_0maker’s file	36.0 / 43.2 GB	13–19 tok/s	36K	One GPU
Runs well	Qwen3-VL-32B-Thinking Alibaba Qwen	33.4B	Q8_0maker’s file	36.0 / 43.2 GB	13–19 tok/s	36K	One GPU
Runs well	Qwen2.5-32B-Instruct Alibaba Qwen	32.8B	Q8_0maker’s file	36.1 / 43.2 GB	13–19 tok/s	32K	One GPU
Runs well	Qwen2.5-Coder-32B-Instruct Alibaba Qwen	32.8B	INT8 (GPTQ)maker’s file	36.3 / 43.2 GB	13–19 tok/s	32K	One GPU
Runs well	QwQ-32B Alibaba Qwen	32.8B	Q8_0maker’s file	36.1 / 43.2 GB	13–19 tok/s	36K	One GPU
Runs well	DeepSeek-R1-Distill-Qwen-32B DeepSeek	32.8B	Q8_0	36.0 / 43.2 GB	13–19 tok/s	32K	One GPU
Runs well	Qwen3-32B Alibaba Qwen	32.8B	Q8_0maker’s file	36.0 / 43.2 GB	13–19 tok/s	36K	One GPU
Runs well	Qwen3-Omni-30B-A3B-Captioner Alibaba Qwen	31.7B	Q8_0	33.7 / 43.2 GB	85–128 tok/s	64K	One GPU
Runs well	Gemma 4 31B IT Google	31.3B	Q8_0	34.5 / 43.2 GB	14–20 tok/s	63K	One GPU
Runs well	GLM-4.7-Flash Zhipu AI	31.2B	Q8_0	32.9 / 43.2 GB	81–121 tok/s	195K	One GPU
Runs well	Qwen3-VL-30B-A3B-Instruct Alibaba Qwen	31.1B	Q8_0maker’s file	32.5 / 43.2 GB	98–148 tok/s	122K	One GPU
Runs well	Qwen3-VL-30B-A3B-Thinking Alibaba Qwen	31.1B	Q8_0maker’s file	32.5 / 43.2 GB	98–148 tok/s	122K	One GPU
Runs well	Qwen3-30B-A3B-Instruct-2507 Alibaba Qwen	30.5B / 3.3B	Q8_0	32.5 / 43.2 GB	111–167 tok/s	122K	One GPU
Runs well	Qwen3-30B-A3B-Thinking-2507 Alibaba Qwen	30.5B / 3.3B	Q8_0	32.5 / 43.2 GB	111–167 tok/s	256K	One GPU
Runs well	Qwen3-30B-A3B Alibaba Qwen	30.5B / 3.3B	Q8_0maker’s file	32.5 / 43.2 GB	111–167 tok/s	128K	One GPU
Runs well	Qwen3-Coder-30B-A3B-Instruct Alibaba Qwen	30.5B / 3.3B	Q8_0	32.5 / 43.2 GB	111–167 tok/s	122K	One GPU
Runs well	Hy-Memory-30B-A3B Tencent	30.1B / 3B	Q8_0maker’s file	32.0 / 43.2 GB	120–180 tok/s	63K	One GPU
Runs well	Granite Switch 4.1 30B IBM	30B	Q8_0maker’s file	35.4 / 43.2 GB	13–20 tok/s	38K	One GPU
Runs well	Qwen3.5-27B Alibaba Qwen	27.8B	Q8_0	29.4 / 43.2 GB	16–24 tok/s	229K	One GPU
Runs well	Qwen3.6-27B Alibaba Qwen	27.8B	Q8_0	29.4 / 43.2 GB	16–24 tok/s	229K	One GPU
Runs well	Qwen3.8-27B Alibaba Qwen	27.8B	Q8_0	29.4 / 43.2 GB	16–24 tok/s	229K	One GPU
Runs well	Gemma 4 26B A4B IT Google	25.8B / 3.8B	Q8_0	27.3 / 43.2 GB	105–157 tok/s	250K	One GPU
Runs well	Magistral Small 1.2 Mistral AI	24B	Q8_0maker’s file	25.8 / 43.2 GB	18–27 tok/s	119K	One GPU
Runs well	Devstral Small 1.0 Mistral AI	23.6B	Q8_0	25.7 / 43.2 GB	18–27 tok/s	120K	One GPU
Runs well	Devstral Small 1.1 Mistral AI	23.6B	Q8_0	25.7 / 43.2 GB	18–27 tok/s	120K	One GPU
Runs well	Magistral Small 1.0 Mistral AI	23.6B	Q8_0	25.7 / 43.2 GB	18–27 tok/s	39K	One GPU
Runs well	Magistral Small 1.1 Mistral AI	23.6B	Q8_0maker’s file	25.8 / 43.2 GB	18–27 tok/s	39K	One GPU
Runs well	ERNIE-4.5-21B-A3B-Thinking Baidu	21.8B / 3B	Q8_0	23.1 / 43.2 GB	131–197 tok/s	128K	One GPU
Runs well	GPT OSS 20B OpenAI	20.9B / 3.6B	MXFP4 (native)maker’s file	13.6 / 43.2 GB	187–280 tok/s	128K	One GPU
Runs well	Qwen2.5-14B-Instruct-1M Alibaba Qwen	14.8B	BF16 (native)maker’s file	30.4 / 43.2 GB	15–23 tok/s	76K	One GPU
Runs well	Qwen2.5-14B-Instruct Alibaba Qwen	14.8B	BF16 (native)maker’s file	30.4 / 43.2 GB	15–23 tok/s	32K	One GPU
Runs well	DeepSeek-R1-Distill-Qwen-14B DeepSeek	14.8B	BF16 (native)maker’s file	30.4 / 43.2 GB	15–23 tok/s	32K	One GPU
Runs well	Qwen3-14B Alibaba Qwen	14.8B	BF16 (native)maker’s file	30.1 / 43.2 GB	16–23 tok/s	128K	One GPU
Runs well	Gemma 3 12B IT Google	12.2B	BF16 (native)maker’s file	26.6 / 43.2 GB	18–26 tok/s	55K	One GPU
Runs well	Qwen2.5-Omni-7B Alibaba Qwen	10.7B	BF16 (native)maker’s file	22.3 / 43.2 GB	21–32 tok/s	32K	One GPU
Runs well	GLM-4.6V-Flash Zhipu AI	10.3B	BF16 (native)maker’s file	20.4 / 43.2 GB	23–34 tok/s	125K	One GPU
Runs well	Qwen3.5-9B Alibaba Qwen	9.7B	BF16 (native)maker’s file	19.1 / 43.2 GB	25–37 tok/s	256K	One GPU
Runs well	Qianfan-VL-8B Baidu	8.8B	BF16 (native)maker’s file	18.2 / 43.2 GB	26–39 tok/s	32K	One GPU
Runs well	Granite Switch 4.1 8B IBM	8.8B	BF16 (native)maker’s file	18.5 / 43.2 GB	25–38 tok/s	128K	One GPU
Runs well	Qwen3-VL-8B-Instruct Alibaba Qwen	8.8B	BF16 (native)maker’s file	18.3 / 43.2 GB	26–38 tok/s	128K	One GPU
Runs well	Qwen3-VL-8B-Thinking Alibaba Qwen	8.8B	BF16 (native)maker’s file	18.3 / 43.2 GB	26–38 tok/s	128K	One GPU
Runs well	pplx-embed-v2-context-9b Perplexity	8.4B	FP32 (native)maker’s file	33.1 / 43.2 GB	14–21 tok/s	256K	One GPU
Runs well	Qwen2.5-VL-7B-Instruct Alibaba Qwen	8.3B	BF16 (native)maker’s file	16.7 / 43.2 GB	28–42 tok/s	125K	One GPU
Runs well	Qwen3-8B Alibaba Qwen	8.2B	BF16 (native)maker’s file	17.1 / 43.2 GB	27–41 tok/s	128K	One GPU
Runs well	DeepSeek-R1-Distill-Llama-8B DeepSeek	8B	BF16 (native)maker’s file	16.7 / 43.2 GB	28–42 tok/s	125K	One GPU
Runs well	Gemma 4 E4B Google	8B	BF16 (native)maker’s file	15.8 / 43.2 GB	30–45 tok/s	125K	One GPU
Runs well	Ling-3.0-tiny Ant Group	7.9B / 1.3B	BF16 (native)maker’s file	15.6 / 43.2 GB	170–255 tok/s	128K	One GPU
Runs well	Qwen2.5-7B-Instruct-1M Alibaba Qwen	7.6B	BF16 (native)maker’s file	15.3 / 43.2 GB	31–46 tok/s	517K	One GPU
Runs well	Qwen2.5-7B-Instruct Alibaba Qwen	7.6B	BF16 (native)maker’s file	15.3 / 43.2 GB	31–46 tok/s	32K	One GPU
Runs well	DeepSeek-R1-Distill-Qwen-7B DeepSeek	7.6B	BF16 (native)maker’s file	15.3 / 43.2 GB	31–46 tok/s	32K	One GPU
Runs well	Mistral-7B-Instruct-v0.1 Mistral AI	7.2B	BF16 (native)maker’s file	15.2 / 43.2 GB	31–46 tok/s	32K	One GPU
Runs well	Gemma 4 E2B Google	5.1B	BF16 (native)maker’s file	10.1 / 43.2 GB	47–70 tok/s	125K	One GPU
Runs well	WeVisOne-VL-4B Tencent	4.8B	BF16 (native)maker’s file	10.6 / 43.2 GB	44–66 tok/s	240K	One GPU
Runs well	Qianfan-OCR Baidu	4.7B	BF16 (native)maker’s file	10.5 / 43.2 GB	45–67 tok/s	31K	One GPU
Runs well	Qwen3.5-4B Alibaba Qwen	4.7B	BF16 (native)maker’s file	9.4 / 43.2 GB	50–75 tok/s	256K	One GPU
Runs well	Qwen3-VL-4B-Instruct Alibaba Qwen	4.4B	BF16 (native)maker’s file	9.9 / 43.2 GB	48–71 tok/s	245K	One GPU
Runs well	Qwen3-4B-Instruct-2507 Alibaba Qwen	4B	BF16 (native)maker’s file	9.1 / 43.2 GB	52–78 tok/s	250K	One GPU
Runs well	Qwen3-4B Alibaba Qwen	4B	BF16 (native)maker’s file	9.1 / 43.2 GB	52–78 tok/s	128K	One GPU
Runs well	DeepSeek-OCR DeepSeek	3.3B	BF16 (native)maker’s file	7.2 / 43.2 GB	172–258 tok/s	8K	One GPU
Runs well	Granite-4.0-H-Micro IBM	3.2B	BF16 (native)maker’s file	6.5 / 43.2 GB	74–112 tok/s	128K	One GPU
Runs well	Qwen3-1.7B Alibaba Qwen	2B	BF16 (native)maker’s file	5.2 / 43.2 GB	96–144 tok/s	40K	One GPU
Runs well	DeepSeek-R1-Distill-Qwen-1.5B DeepSeek	1.8B	BF16 (native)maker’s file	4.0 / 43.2 GB	127–190 tok/s	125K	One GPU
Runs well	GLM-OCR Zhipu AI	1.3B	BF16 (native)maker’s file	3.5 / 43.2 GB	151–226 tok/s	128K	One GPU
Runs well	Qwen3-0.6B Alibaba Qwen	0.8B	BF16 (native)maker’s file	2.8 / 43.2 GB	196–295 tok/s	40K	One GPU
Runs well	EmbeddingGemma 2 Google	0.7B	BF16 (native)maker’s file	2.0 / 43.2 GB	304–457 tok/s	256K	One GPU
Runs well	Qwen3-Embedding-0.6B Alibaba Qwen	0.6B	BF16 (native)maker’s file	2.5 / 43.2 GB	225–338 tok/s	32K	One GPU
Runs well	bge-reranker-v2-m3 BAAI	0.6B	FP32 (native)maker’s file	3.4 / 43.2 GB	156–234 tok/s	8K	One GPU
Runs well	bge-m3-unsupervised BAAI	0.6B	FP32 (native)maker’s file	3.4 / 43.2 GB	156–234 tok/s	8K	One GPU
Runs well	bge-large-en-v1.5 BAAI	0.3B	FP32 (native)maker’s file	1.8 / 43.2 GB	345–518 tok/s	512	One GPU
Runs well	bge-reranker-base BAAI	0.3B	FP32 (native)maker’s file	1.6 / 43.2 GB	424–637 tok/s	514	One GPU
Runs well	bge-base-en-v1.5 BAAI	0.1B	FP32 (native)maker’s file	0.9 / 43.2 GB	1051–1576 tok/s	512	One GPU
Runs well	bge-small-en-v1.5 BAAI	0B	FP32 (native)maker’s file	0.6 / 43.2 GB	3359–5038 tok/s	512	One GPU
Runs, slowly	Qwen2.5-VL-72B-Instruct Alibaba Qwen	73.4B	Q4_0	42.9 / 43.2 GB	11–16 tok/s	9K	One GPU
Runs, slowly	Qwen2-VL-72B-Instruct Alibaba Qwen	73.4B	Q4_0	42.9 / 43.2 GB	11–16 tok/s	9K	One GPU
Runs, slowly	Qwen2.5-72B-Instruct Alibaba Qwen	72.7B	Q4_0maker’s file	43.0 / 43.2 GB	11–16 tok/s	9K	One GPU
Runs, slowly	Qianfan-VL-70B Baidu	71.8B	Q4_0	42.0 / 43.2 GB	11–17 tok/s	12K	One GPU
Runs, slowly	DeepSeek-R1-Distill-Llama-70B DeepSeek	70.6B	Q4_0	41.3 / 43.2 GB	11–17 tok/s	14K	One GPU
Needs system memory	Ming-3.0-audio-flash Ant Group	128.2B / 6.5B	Q5_K_M	89.5 GB, 46.5 in system memory	16–25 tok/s	—	23/42 layers in system memory
Needs system memory	Ling-3.0-flash Ant Group	127.5B / 5.1B	Q5_K_Mmaker’s file	88.8 GB, 46.1 in system memory	21–31 tok/s	—	23/42 layers in system memory
Needs system memory	Qwen3.5-122B-A10B Alibaba Qwen	125.1B / 10B	Q4_K_M	74.5 GB, 32.4 in system memory	14–22 tok/s	—	22/48 layers in system memory
Needs system memory	Ling-3.0-flash-VL Ant Group	124.8B / 5.5B	Q5_K_M	87.2 GB, 45.3 in system memory	19–29 tok/s	—	23/42 layers in system memory
Needs system memory	gpt-oss-120b OpenAI	116.8B / 5.1B	MXFP4 (native)maker’s file	64.1 GB, 21.9 in system memory	37–56 tok/s	—	13/36 layers in system memory
Needs system memory	GLM-4.5-Air Zhipu AI	110.5B	IQ4_XS	58.8 GB, 16.6 in system memory	13–20 tok/s	—	14/46 layers in system memory
Needs system memory	GLM-4.5V Zhipu AI	107.7B / 12B	Q4_K_M	65.4 GB, 22.5 in system memory	14–22 tok/s	—	17/46 layers in system memory
Needs system memory	GLM-4.6V Zhipu AI	107.7B	Q4_0	60.7 GB, 18.4 in system memory	14–22 tok/s	—	15/46 layers in system memory
Needs system memory	Ling-2.6-flash Ant Group	107.5B / 7.4B	Q6_K	86.6 GB, 43.7 in system memory	13–19 tok/s	—	17/32 layers in system memory

Estimates from the makers’ Hugging Face repositories (as of 2026-11-06); filtered views aren’t indexed. How it’s estimated