What AI models can the UDOO BOLT V8 (16 GB) run?

Unified memory: 16.0 GB
Usable for models: 8.0 GB
Memory bandwidth: 38 GB/s
Runs models on: GPU (Vulkan)
Released: 2019

337 / 621 LLMs run Best: Ling 3.0 Tiny (8B-A1.3B) 49 / 61 Image models run Best: FLUX.2 [klein] 4B 7 / 43 Video models run Best: LTX-Video 2B 62 / 70 Decision models run Best: GLiNER2.5 Decide

Models run on the GPU (Vulkan) here, sharing the board’s memory with the system. We plan around 8.0 GB of the 16.0 GB (what the operating system leaves free for a model). Radeon Vega 8 graphics (8 compute units); no NPU. llama.cpp uses it through Vulkan (ROCm doesn’t support this GPU).

More about this hardware

Maker	AMD
Type	Single-board computer or edge AI board
GPU share of memory	50% (what the GPU can typically be given for a model)
Chip	AMD Ryzen Embedded V1605B
AI accelerator	Radeon Vega 8 graphics (8 compute units); no NPU. llama.cpp uses it through Vulkan (ROCm doesn’t support this GPU).
Boards with this chip	UDOO BOLT V8 · UDOO BOLT GEAR
Memory type	DDR4-2400, two SO-DIMM slots (dual channel)
Bandwidth figure	38.4 GB/s, the chip’s rated memory speed
Note	4-core, 8-thread Ryzen Embedded V1605B, up to 32 GB in two SO-DIMMs, plus an Arduino Leonardo-compatible microcontroller. We assume the GPU can use about half of the RAM. GPU figure from 8 CUs at 1.1 GHz.
Specifications	shop.seco.com

Apps that run models well on the UDOO BOLT V8 (16 GB)

Windows

Linux

For a typical model that fits in memory. Each model page picks the best app for that model on this hardware. All apps

1 product with the UDOO BOLT V8 (16 GB)

UDOO BOLT V8UDOO · Board · 8, 16 or 32 GBProduct page (opens in a new tab)

Best LLMs for the UDOO BOLT V8 (16 GB)

Quality	Model	Quant	Memory	Speed	Runs
57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.	Ling 3.0 Tiny (8B-A1.3B)Ant Group (inclusionAI)	`Q4_K_M`	6.3 GB	28.3 tok/s	Runs well
76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.	K2 Horizon 7BInstitute of Foundation Models	`Q4_K_M`	7.9 GB	4.5 tok/s	Slowtight fit
74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.	MiMo V2.6 Distill Qwen 9BXiaomi	`Q4_K_M`	7.2 GB	4.3 tok/s	Slowtight fit
74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.	SenseNova Loop 9B PreviewSenseTime	`Q4_K_M`	7.6 GB	4.2 tok/s	Slowtight fit
73Great quality (A) · 73 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.	Ornith 1.5 9BDeepReinforce	`Q4_K_M`	7.4 GB	4.2 tok/s	Slowtight fit
72Great quality (A) · 72 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3.5 9BAlibaba	`Q4_K_M`	7.4 GB	4.2 tok/s	Slowtight fit
58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.	Mellum2.1 Thinking (12B-A2.5B)JetBrains	`Q3_K_M`	7.3 GB	19.7 tok/s	Runs welltight fit
71Great quality (A) · 71 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.	Ornith 1.0 9BDeepReinforce	`Q4_K_M`	7.4 GB	4.2 tok/s	Slowtight fit
71Great quality (A) · 71 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.	TMax 9BAi2	`Q5_K_M`	7.9 GB	3.7 tok/s	Slowtight fit
69Good quality (B) · 69 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.	Gemma 4 12BGoogle	`Q3_K_M`	7.8 GB	4.4 tok/s	Slowtight fit
58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.	Nemotron 3.5 Bolt E4BNVIDIA	`Q3_K_M`	5.3 GB	11.7 tok/s	Runs well
58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.	Gemma 4 E2BGoogle	`Q4_K_M`	4.4 GB	17.6 tok/s	Runs well

Best Image models for the UDOO BOLT V8 (16 GB)

Quality	Model	Quant	Memory	Speed	Runs
76Great quality (A) · 76 of 100: how capable the model is at FP8, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.	FLUX.2 [klein] 4BBlack Forest Labs	`FP8`	6.2 GB	21 s	Runs wellencoder unloaded after use
84Great quality (A) · 84 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.	FLUX 3 Image KleinBlack Forest Labs	`Q4 GGUF`	5.7 GB	2.7 min	Very slowencoder unloaded after use
52Fair quality (C) · 52 of 100: how capable the model is at FP8, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.	SDXL-Lightning (4-step)ByteDance	`FP8`	5.6 GB	14 s	Runs well
78Great quality (A) · 78 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.	Z-Image TurboAlibaba (Tongyi)	`Q4 GGUF`	6.1 GB	70 s	Slowencoder unloaded after use
56Good quality (B) · 56 of 100: how capable the model is at FP8, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.	DreamShaper XL v2 TurboLykon	`FP8`	5.6 GB	26 s	Runs well
79Great quality (A) · 79 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.	ERNIE-Image TurboBaidu	`Q4 GGUF`	7.4 GB	1.5 min	Slowtight fit · encoder unloaded after use

Best Video models for the UDOO BOLT V8 (16 GB)

Quality	Model	Quant	Memory	Speed	Runs
49Fair quality (C) · 49 of 100: how capable the model is at FP8, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.	LTX-Video 2BLightricks	`FP8`	6.1 GB	8.8 min	Runs wellencoder unloaded after use
35Basic quality (D) · 35 of 100: how capable the model is at FP16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.	AnimateDiff v3 (SD 1.5)Shanghai AI Lab	`FP16`	4.7 GB	7.5 min	Runs well
44Fair quality (C) · 44 of 100: how capable the model is at FP8, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.	CogVideoX 2BZhipu AI	`FP8`	6.2 GB	21.1 min	Slowencoder unloaded after use
53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.	Wan 2.1 T2V 1.3BAlibaba	`FP8`	7.1 GB	84.6 min	Very slowtight fit · encoder unloaded after use
53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.	CogVideoX 5BZhipu AI	`FP8`	5.9 GB	78.5 min	Very slowCPU offload

Best Decision models for the UDOO BOLT V8 (16 GB)

Quality	Model	Quant	Memory	Speed	Runs
80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking.	GLiNER2.5 DecideFastino	`Q8_0`	1.2 GB	102 ms	Runs great
74Great quality (A) · 74 of 100: how capable the model is at F16, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking.	GLiClass ModernBERT Large v3Knowledgator	`F16`	1.5 GB	96 ms	Runs great
76Great quality (A) · 76 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking.	Llama Prompt Guard 2 86MMeta	`Q8_0`	1.0 GB	116 ms	Runs great
86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking.	Jina Reranker v3.5Jina AI	`Q8_0`	2.1 GB	253 ms	Runs well
78Great quality (A) · 78 of 100: how capable the model is at F16, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking.	OpenAI Privacy FilterOpenAI	`F16`	3.8 GB	15 ms	Runs great
80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.	FRIDA-DecisionsSber AI	`Q8_0`	1.7 GB	168 ms	Runs well
72Great quality (A) · 72 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.	DeBERTa v3 Large Zero-shot v2.0Moritz Laurer	`Q8_0`	1.2 GB	92 ms	Runs great
84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.	Jina Reranker v3Jina AI	`Q8_0`	2.1 GB	253 ms	Runs well

Best LLMs by task on this hardware Open in Model Finder

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.