What are the best models to run on Radeon PRO W6800 (32GB)?

Based on model rankings and 32 GB usable VRAM: Top Overall: Qwen 3.8 27B (INT4) ~26 tok/s. Top Coding: Qwen3.5-27B (INT4) ~26 tok/s. Optimal Daily Driver: Phi-4 Reasoning Plus (INT4) ~34 tok/s. Maximum Model Size: Kimi Linear 48B A3B Instruct (INT4) ~37 tok/s.

How are VRAM, throughput, and latency calculated?

Calculations are determined using apxml.com modeling, combining LLM architecture analysis with GPU hardware physics. VRAM and Context Scaling: Memory requirements are determined from model architecture, including parameter count, layer configuration, and attention structure. The KV cache footprint scales deterministically based on context length, batch size, and cache precision. Throughput (TPS): Token generation is calculated in the memory-bandwidth-bound decode phase, measuring the time required to stream model weights and KV cache relative to hardware memory bandwidth. Latency (TTFT): Time to first token is calculated from the compute operations required during prompt prefill relative to hardware tensor compute capacity.

How accurate are these estimates?

Calculations are calibrated against empirical ground-truth benchmark runs across diverse architectures and hardware. Because the underlying mechanics are benchmark-calibrated, estimates remain accurate across different configurations without needing to run physical tests for every scenario. VRAM Accuracy: Memory estimates are deterministic and closely match actual allocation. Minor differences typically stay within 3% to 5% due to CUDA runtime overhead or memory allocator fragmentation. Speed and Latency Accuracy: Throughput and TTFT typically vary within 5% to 10% depending on the specific inference runtime, kernel implementations, and system power limits.

Best Models to Run on Radeon PRO W6800 (32GB) (October 2026)

Rank	Model	Parameters	Precision	TPS (Approx.)	TTFT
#33	Qwen 3.8 27B	27B	INT4 Q8	26 tok/s 14 tok/s	~8.3s ~9.1s
#48	Agnes 3.0 Flash	33B	INT4	22 tok/s	~10.1s
#72	K2 Horizon MoVA 36B A4B	36B (4B active)	INT4	104 tok/s	~1.6s
#83	Qwen3.5-27B	27B	INT4 Q8	26 tok/s 14 tok/s	~8.3s ~9.1s
#92	Sarvam-30B	32B (2.4B active)	INT4	133 tok/s	~1.1s
#94	Qwen3.6 35B A3B	35B (3B active)	INT4	120 tok/s	~1.3s
#96	Muse Glimmer 30B	30B	INT4 Q8	24 tok/s 12 tok/s	~9.3s ~10.9s
#100	Phi-4 Reasoning Plus	14B	INT4 Q8 FP16	34 tok/s 23 tok/s 12 tok/s	~4.4s ~4.4s ~5.2s
#101	MiMo V2 Flash	15B (309B active)	INT4 Q8	3 tok/s 1 tok/s	~91.2s ~91.6s
#108	Gemma 4 26B A4B	25.2B (3.8B active)	INT4 Q8	111 tok/s 74 tok/s	~1.5s ~1.6s
#109	Gemma 4 12B	11.95B	INT4 Q8 FP16	39 tok/s 27 tok/s 15 tok/s	~3.8s ~3.8s ~4.1s
#113	Qwen3.5-9B	9B	INT4 Q8 FP16	68 tok/s 41 tok/s 22 tok/s	~2.8s ~2.9s ~2.9s
#114	Qwen3.5-35B-A3B	35B (3B active)	INT4	120 tok/s	~1.3s
#118	K2 Horizon 7B	7B	INT4 Q8 FP16	83 tok/s 52 tok/s 28 tok/s	~2.2s ~2.2s ~2.2s
#128	NVIDIA Nemotron 3 Nano 30B-A3B	3.5B (30B active)	INT4 Q8 FP16	23 tok/s 13 tok/s 7 tok/s	~9.0s ~9.0s ~9.1s
#129	Gemma 4 31B	30.7B	INT4 Q8	23 tok/s 12 tok/s	~9.5s ~11.2s
#131	Nemotron 3.5 Lightning	30B (3B active)	INT4	49 tok/s	~1.3s
#132	Qwen3.5-4B	4B	INT4 Q8 FP16	122 tok/s 81 tok/s 46 tok/s	~1.3s ~1.3s ~1.3s
#133	Qwen3-30B-A3B	30B (3B active)	INT4 Q8	122 tok/s 80 tok/s	~1.3s ~1.5s
#136	GPT-OSS 20B	21B (3.6B active)	INT4 Q8	54 tok/s 45 tok/s	~1.4s ~1.5s
#146	Granite 4.2 8B	8B	INT4 Q8 FP16	75 tok/s 46 tok/s 25 tok/s	~2.5s ~2.5s ~2.6s
#150	Gemma 4 E4B	8B	INT4 Q8 FP16	75 tok/s 46 tok/s 25 tok/s	~2.5s ~2.5s ~2.6s
#151	Nemotron 3.5 Lightning 30B A3B	30B (3B active)	INT4 Q8	122 tok/s 80 tok/s	~1.3s ~1.5s
#153	Qwen3-32B	32B	INT4	22 tok/s	~9.9s
#155	Mistral Large 3	41B (675B active)	INT4	1 tok/s	~234.2s
#156	GLM-4	32B	INT4	17 tok/s	~9.9s
#158	GLM-4V	9B	INT4 Q8 FP16	49 tok/s 34 tok/s 20 tok/s	~2.8s ~2.9s ~2.9s
#159	Gemma 3 27B	27B	INT4 Q8	26 tok/s 14 tok/s	~8.3s ~9.1s
#160	Phi-4	14B	INT4 Q8 FP16	47 tok/s 28 tok/s 14 tok/s	~4.4s ~4.4s ~4.8s
#162	DeepSeek-R1 32B	32B	INT4 Q8	23 tok/s 12 tok/s	~9.9s ~11.6s
#164	Qwen2.5-32B	32B	INT4	22 tok/s	~9.9s
#168	Magistral Small	24B	INT4 Q8	22 tok/s 14 tok/s	~7.4s ~8.1s
#169	OLMo 3 7B Think	7B	INT4 Q8 FP16	60 tok/s 42 tok/s 25 tok/s	~2.2s ~2.2s ~2.3s
#170	OLMo 3.1 32B Instruct	32B	INT4	17 tok/s	~9.9s
#172	DeepSeek-R1 14B	14B	INT4 Q8 FP16	48 tok/s 28 tok/s 14 tok/s	~4.4s ~4.4s ~4.8s
#173	Ministral 3 14B	14B	INT4 Q8 FP16	34 tok/s 23 tok/s 12 tok/s	~4.4s ~4.4s ~5.2s
#177	Gemma 3 12B	12B	INT4 Q8 FP16	54 tok/s 32 tok/s 17 tok/s	~3.8s ~3.8s ~3.8s
#180	OLMo 3 32B Base	32B	INT4	17 tok/s	~9.9s
#181	Mistral-Small-2501	24B	INT4 Q8	29 tok/s 16 tok/s	~7.4s ~8.1s
#182	Ministral 3 8B	8B	INT4 Q8 FP16	54 tok/s 38 tok/s 22 tok/s	~2.5s ~2.5s ~2.6s
#183	Qwen3.5-2B	2B	INT4 Q8 FP16	178 tok/s 130 tok/s 81 tok/s	~695 ms ~697 ms ~702 ms
#184	MiniCPM5-2B	2B	INT4 Q8 FP16	178 tok/s 130 tok/s 81 tok/s	~695 ms ~697 ms ~702 ms
#185	Qwen2.5-14B	14B	INT4 Q8 FP16	47 tok/s 28 tok/s 14 tok/s	~4.4s ~4.4s ~4.8s
#186	Gemma 2 27B	27B	INT4 Q8	26 tok/s 14 tok/s	~8.3s ~9.1s
#187	OLMo 3.1 32B Think	32B	INT4	17 tok/s	~9.9s
#188	Gemma 4 E2B	5.1B	INT4 Q8 FP16	104 tok/s 67 tok/s 38 tok/s	~1.6s ~1.6s ~1.7s
#189	Qwen3-4B	4B	INT4 Q8 FP16	122 tok/s 81 tok/s 46 tok/s	~1.3s ~1.3s ~1.3s
#190	DeepSeek-R1 8B	8B	INT4 Q8 FP16	76 tok/s 47 tok/s 25 tok/s	~2.5s ~2.5s ~2.6s
#193	Ministral 3 3B	3B	INT4 Q8 FP16	99 tok/s 77 tok/s 50 tok/s	~1.0s ~1.0s ~1.0s
#195	Qwen3-14B	14B	INT4 Q8 FP16	47 tok/s 28 tok/s 14 tok/s	~4.4s ~4.4s ~4.8s
#196	Kimi Linear 48B A3B Instruct	48B (3B active)	INT4	37 tok/s	~1.7s
#197	Gemma 2 9B	9B	INT4 Q8 FP16	68 tok/s 41 tok/s 22 tok/s	~2.8s ~2.9s ~2.9s
#198	Qwen2.5-7B	7B	INT4 Q8 FP16	83 tok/s 52 tok/s 28 tok/s	~2.2s ~2.2s ~2.2s
#199	Qwen3-8B	8B	INT4 Q8 FP16	75 tok/s 46 tok/s 25 tok/s	~2.5s ~2.5s ~2.6s
#200	Gemma 3 4B	4B	INT4 Q8 FP16	122 tok/s 81 tok/s 46 tok/s	~1.3s ~1.3s ~1.3s
#201	DeepSeek-R1 7B	7B	INT4 Q8 FP16	85 tok/s 52 tok/s 28 tok/s	~2.2s ~2.2s ~2.2s
#202	Llama 3.1 8B	8B	INT4 Q8 FP16	75 tok/s 46 tok/s 25 tok/s	~2.5s ~2.5s ~2.6s
#204	Qwen3-1.7B	1.7B	INT4 Q8 FP16	193 tok/s 144 tok/s 92 tok/s	~595 ms ~597 ms ~601 ms
#205	Command R	35B	INT4	16 tok/s	~10.8s
#206	Gemma 3 270M	0.27B	INT4 Q8 FP16	296 tok/s 275 tok/s 235 tok/s	~98 ms ~98 ms ~98 ms
#208	Llama 3 8B	8B	INT4 Q8 FP16	75 tok/s 46 tok/s 25 tok/s	~2.5s ~2.5s ~2.6s
#209	Qwen3-0.6B	0.6B	INT4 Q8 FP16	280 tok/s 239 tok/s 180 tok/s	~212 ms ~213 ms ~214 ms
#210	Phi-4-Mini	3.8B	INT4 Q8 FP16	126 tok/s 84 tok/s 48 tok/s	~1.2s ~1.2s ~1.3s
#211	Mixtral-8x7B-v0.1	46.7B (7B active)	INT4	70 tok/s	~2.8s
#212	Ministral-8B-2410	8B	INT4 Q8 FP16	75 tok/s 46 tok/s 25 tok/s	~2.5s ~2.5s ~2.6s
#213	DeepSeek-R1 1.5B	1.5B	INT4 Q8 FP16	204 tok/s 155 tok/s 101 tok/s	~527 ms ~528 ms ~532 ms
#214	Llama 3.2 3B	3B	INT4 Q8 FP16	145 tok/s 100 tok/s 59 tok/s	~999 ms ~1.0s ~1.0s
#215	Qwen3.5-0.8B	0.8B	INT4 Q8 FP16	258 tok/s 213 tok/s 153 tok/s	~285 ms ~286 ms ~288 ms
#216	Phi-3-mini	3.8B	INT4 Q8 FP16	126 tok/s 84 tok/s 48 tok/s	~1.2s ~1.2s ~1.3s
#217	Gemma 3n E2B IT	6B (2B active)	INT4 Q8 FP16	99 tok/s 84 tok/s 61 tok/s	~746 ms ~748 ms ~752 ms
#218	Mistral-7B-Instruct-v0.1	7.3B	INT4 Q8 FP16	80 tok/s 50 tok/s 27 tok/s	~2.3s ~2.3s ~2.3s
#219	Llama 3.2 1B	1B	INT4 Q8 FP16	238 tok/s 191 tok/s 133 tok/s	~361 ms ~362 ms ~364 ms
#220	Gemma 2 2B	2B	INT4 Q8 FP16	178 tok/s 130 tok/s 81 tok/s	~695 ms ~697 ms ~702 ms
#221	Phi-3-medium	14B	INT4 Q8 FP16	47 tok/s 28 tok/s 14 tok/s	~4.4s ~4.4s ~4.8s
#222	OLMo 3 7B Instruct	7B	INT4 Q8 FP16	60 tok/s 42 tok/s 25 tok/s	~2.2s ~2.2s ~2.3s
#223	Yi-34B	34B	INT4	17 tok/s	~10.5s
#224	Qwen2-7B	7B	INT4 Q8 FP16	83 tok/s 52 tok/s 28 tok/s	~2.2s ~2.2s ~2.2s
#225	Phi-3-small	7B	INT4 Q8 FP16	83 tok/s 52 tok/s 28 tok/s	~2.2s ~2.2s ~2.2s
#226	Gemma 3 1B	1B	INT4 Q8 FP16	238 tok/s 191 tok/s 133 tok/s	~361 ms ~362 ms ~364 ms
#227	Mistral-7B-Instruct-v0.2	7.3B	INT4 Q8 FP16	80 tok/s 50 tok/s 27 tok/s	~2.3s ~2.3s ~2.3s
#229	Gemma 1 7B	7B	INT4 Q8 FP16	60 tok/s 42 tok/s 25 tok/s	~2.2s ~2.2s ~2.3s
#230	Gemma 1 2B	2B	INT4 Q8 FP16	189 tok/s 135 tok/s 83 tok/s	~695 ms ~697 ms ~701 ms
#231	ChatGLM3-6B	6B	INT4 Q8 FP16	66 tok/s 48 tok/s 29 tok/s	~1.9s ~1.9s ~1.9s
#232	ChatGLM2-6B	6B	INT4 Q8 FP16	66 tok/s 48 tok/s 29 tok/s	~1.9s ~1.9s ~1.9s
#233	ChatGLM-6B	6B	INT4 Q8 FP16	66 tok/s 48 tok/s 29 tok/s	~1.9s ~1.9s ~1.9s
Unranked Models (Sorted by Speed)
-	Qwen2-0.5B	0.5B	INT4 Q8 FP16	293 tok/s 254 tok/s 197 tok/s	~176 ms ~177 ms ~178 ms
-	Qwen2.5-0.5B	0.5B	INT4 Q8 FP16	293 tok/s 254 tok/s 197 tok/s	~176 ms ~177 ms ~178 ms
-	ERNIE-4.5-0.3B	0.3B	INT4 Q8 FP16	288 tok/s 266 tok/s 225 tok/s	~108 ms ~108 ms ~109 ms
-	ERNIE-4.5-0.3B-Base	0.3B	INT4 Q8 FP16	288 tok/s 266 tok/s 225 tok/s	~108 ms ~108 ms ~109 ms
-	Falcon-1B	1B	INT4 Q8 FP16	249 tok/s 198 tok/s 136 tok/s	~361 ms ~362 ms ~364 ms
-	Falcon3-1B	1B	INT4 Q8 FP16	238 tok/s 191 tok/s 133 tok/s	~361 ms ~362 ms ~364 ms
-	Qwen2-1.5B	1.5B	INT4 Q8 FP16	204 tok/s 155 tok/s 101 tok/s	~527 ms ~528 ms ~532 ms
-	Qwen2.5-1.5B	1.5B	INT4 Q8 FP16	204 tok/s 155 tok/s 101 tok/s	~527 ms ~528 ms ~532 ms
-	Spark X2.5 1.7B	1.7B	INT4 Q8 FP16	193 tok/s 144 tok/s 92 tok/s	~595 ms ~597 ms ~601 ms
-	Hy-MT2 1.8B	1.8B	INT4 Q8 FP16	188 tok/s 139 tok/s 88 tok/s	~626 ms ~628 ms ~632 ms
-	Falcon-3B	3B	INT4 Q8 FP16	153 tok/s 103 tok/s 60 tok/s	~999 ms ~1.0s ~1.0s
-	CroissantLLM Base	1.3B	INT4 Q8 FP16	150 tok/s 128 tok/s 92 tok/s	~461 ms ~462 ms ~465 ms
-	Phi-1	1.3B	INT4 Q8 FP16	150 tok/s 128 tok/s 92 tok/s	~461 ms ~462 ms ~465 ms
-	Phi-1.5	1.3B	INT4 Q8 FP16	150 tok/s 128 tok/s 92 tok/s	~461 ms ~462 ms ~465 ms
-	DeepSeek-R1 3B	3B	INT4 Q8 FP16	147 tok/s 101 tok/s 59 tok/s	~999 ms ~1.0s ~1.0s
-	Falcon3-3B	3B	INT4 Q8 FP16	145 tok/s 100 tok/s 59 tok/s	~999 ms ~1.0s ~1.0s
-	Qwen2.5-3B	3B	INT4 Q8 FP16	145 tok/s 100 tok/s 59 tok/s	~999 ms ~1.0s ~1.0s
-	ERNIE-4.5-21B-A3B	21B (3B active)	INT4 Q8	127 tok/s 92 tok/s	~1.2s ~1.2s
-	ERNIE-4.5-21B-A3B-Base	21B (3B active)	INT4 Q8	127 tok/s 92 tok/s	~1.2s ~1.2s
-	ERNIE-4.5-VL-28B-A3B	28B (3B active)	INT4 Q8	123 tok/s 85 tok/s	~1.3s ~1.4s
-	ERNIE-4.5-VL-28B-A3B-Base	28B (3B active)	INT4 Q8	123 tok/s 85 tok/s	~1.3s ~1.4s
-	Hy-MT2 30B A3B	30B (3B active)	INT4 Q8	122 tok/s 80 tok/s	~1.3s ~1.5s
-	Spark X2.5 4B	4B	INT4 Q8 FP16	122 tok/s 81 tok/s 46 tok/s	~1.3s ~1.3s ~1.3s
-	Phi-2	2.7B	INT4 Q8 FP16	104 tok/s 82 tok/s 54 tok/s	~911 ms ~914 ms ~920 ms
-	MaLLaM-3B	3B	INT4 Q8 FP16	99 tok/s 77 tok/s 50 tok/s	~1.0s ~1.0s ~1.0s
-	SmolLM3 3B	3B	INT4 Q8 FP16	99 tok/s 77 tok/s 50 tok/s	~1.0s ~1.0s ~1.0s
-	Falcon-7B	7B	INT4 Q8 FP16	86 tok/s 53 tok/s 29 tok/s	~2.2s ~2.2s ~2.2s
-	Falcon3-7B	7B	INT4 Q8 FP16	83 tok/s 52 tok/s 28 tok/s	~2.2s ~2.2s ~2.2s
-	Hy-MT2 7B	7B	INT4 Q8 FP16	83 tok/s 52 tok/s 28 tok/s	~2.2s ~2.2s ~2.2s
-	Mistral-7B-v0.1	7.3B	INT4 Q8 FP16	80 tok/s 50 tok/s 27 tok/s	~2.3s ~2.3s ~2.3s
-	LensVLM 9B	9B	INT4 Q8 FP16	68 tok/s 41 tok/s 22 tok/s	~2.8s ~2.9s ~2.9s
-	MiMo V2.6 Distill Qwen 9B	9B	INT4 Q8 FP16	68 tok/s 41 tok/s 22 tok/s	~2.8s ~2.9s ~2.9s
-	ChatGLM3-6B-32K	6B	INT4 Q8 FP16	66 tok/s 48 tok/s 29 tok/s	~1.9s ~1.9s ~1.9s
-	Yi-6B	6B	INT4 Q8 FP16	66 tok/s 48 tok/s 29 tok/s	~1.9s ~1.9s ~1.9s
-	Falcon3-10B	10B	INT4 Q8 FP16	62 tok/s 38 tok/s 20 tok/s	~3.2s ~3.2s ~3.2s
-	Kimi-VL-A3B-Instruct	16B (3B active)	INT4 Q8	62 tok/s 54 tok/s	~1.2s ~1.2s
-	Falcon2-11B	11B	INT4 Q8 FP16	60 tok/s 35 tok/s 19 tok/s	~3.5s ~3.5s ~3.5s
-	Hunyuan Lite	7B	INT4 Q8 FP16	60 tok/s 42 tok/s 25 tok/s	~2.2s ~2.2s ~2.3s
-	OLMo 3 7B Base	7B	INT4 Q8 FP16	60 tok/s 42 tok/s 25 tok/s	~2.2s ~2.2s ~2.3s
-	SEA-LION-7B	7.1B	INT4 Q8 FP16	59 tok/s 42 tok/s 25 tok/s	~2.3s ~2.3s ~2.3s
-	SEA-LION-7B-Instruct	7.1B	INT4 Q8 FP16	59 tok/s 42 tok/s 25 tok/s	~2.3s ~2.3s ~2.3s
-	Sahabat-AI-Llama3-8B-Instruct	8B	INT4 Q8 FP16	54 tok/s 38 tok/s 22 tok/s	~2.5s ~2.5s ~2.6s
-	Typhoon-2-8B	8B	INT4 Q8 FP16	54 tok/s 38 tok/s 22 tok/s	~2.5s ~2.5s ~2.6s
-	GLM-4-9B	9B	INT4 Q8 FP16	49 tok/s 34 tok/s 20 tok/s	~2.8s ~2.9s ~2.9s
-	GLM-4-9B-Chat	9B	INT4 Q8 FP16	49 tok/s 34 tok/s 20 tok/s	~2.8s ~2.9s ~2.9s
-	GLM-4-9B-Chat-1M	9B	INT4 Q8 FP16	49 tok/s 34 tok/s 20 tok/s	~2.8s ~2.9s ~2.9s
-	Sahabat-AI-Gemma2-9B	9.2B	INT4 Q8 FP16	49 tok/s 34 tok/s 20 tok/s	~2.9s ~2.9s ~2.9s
-	Sahabat-AI-Gemma2-9B-Instruct	9.2B	INT4 Q8 FP16	49 tok/s 34 tok/s 20 tok/s	~2.9s ~2.9s ~2.9s
-	Yi-9B	9B	INT4 Q8 FP16	49 tok/s 34 tok/s 20 tok/s	~2.8s ~2.9s ~2.9s
-	GreenMind-14B-R1	14B	INT4 Q8 FP16	34 tok/s 23 tok/s 12 tok/s	~4.4s ~4.4s ~5.2s
-	Falcon-40B	40B	INT4	19 tok/s	~12.3s

Radeon PRO W6800 (32GB)

VRAM Scaling by Context Length

Best Models to Run on Radeon PRO W6800 (32GB)

Inference Capacity

Fine-Tuning Capacity

Workload Recommendations

Frequently Asked Questions