ASUS · GB10 · AI box

Best AI Models for ASUS Ascent GX10 (128 GB)

Runs 14B and 120B MoE models well; 27–31B and 70B fit but are slow (10 and 4 tok/s).

128 GB unified119 GB for models273 GB/s125 TFLOPS FP162025

GB10 from

ASUS Ascent GX10$2,999 DGX Spark$3,999

What LLMs can the ASUS Ascent GX10 run?

#	Model	Speed	Quant · Memory
1	Qwen3.6 35B A3BAlibabaHow to run → Q4_K_M · 22.0 GB · 49.2 t/s	49.2 tok/s	Q4_K_M · 22.0 GB
2	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 54.1 t/s	54.1 tok/s	Q4_K_M · 16.5 GB
3	Qwen3 30B A3B Thinking 2507Alibaba Q4_K_M · 19.4 GB · 61.0 t/s	61.0 tok/s	Q4_K_M · 19.4 GB
4	GLM 4.5 AirZ.ai Q4_K_M · 67.6 GB · 18.0 t/s	18.0 tok/s	Q4_K_M · 67.6 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 74.9 t/s	74.9 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	Quant · Memory
1	Qwen3.6 35B A3BAlibabaHow to run → Q4_K_M · 22.0 GB · 49.2 t/s	49.2 tok/s	Q4_K_M · 22.0 GB
2	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 54.1 t/s	54.1 tok/s	Q4_K_M · 16.5 GB
3	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 58.8 t/s	58.8 tok/s	Q4_K_M · 13.1 GB
4	GPT OSS 120BOpenAI Q4_K_M · 70.8 GB · 43.2 t/s	43.2 tok/s	Q4_K_M · 70.8 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 74.9 t/s	74.9 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	Quant · Memory
1	Qwen3.6 35B A3BAlibabaHow to run → Q4_K_M · 22.0 GB · 49.2 t/s	49.2 tok/s	Q4_K_M · 22.0 GB
2	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 54.1 t/s	54.1 tok/s	Q4_K_M · 16.5 GB
3	Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 27.9 t/s	27.9 tok/s	Q4_K_M · 6.6 GB
4	GPT OSS 120BOpenAI Q4_K_M · 70.8 GB · 43.2 t/s	43.2 tok/s	Q4_K_M · 70.8 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 74.9 t/s	74.9 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	Quant · Memory
1	Qwen3.6 35B A3BAlibabaHow to run → Q4_K_M · 22.0 GB · 49.2 t/s	49.2 tok/s	Q4_K_M · 22.0 GB
2	Qwen3.8 27BAlibaba Q4_K_M · 17.9 GB · 10.2 t/s	10.2 tok/s	Q4_K_M · 17.9 GB
3	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 10.2 t/s	10.2 tok/s	Q4_K_M · 17.9 GB
4	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 74.9 t/s	74.9 tok/s	Q4_K_M · 19.3 GB
5	GLM 4.7 FlashZ.ai Q4_K_M · 19.9 GB · 47.2 t/s	47.2 tok/s	Q4_K_M · 19.9 GB

#	Model	Speed ↓	Quant · Memory
1	Qwen3 30B A3B Thinking 2507AlibabaHow to run → Q4_K_M · 19.4 GB · 61.0 t/s	61.0 tok/s	Q4_K_M · 19.4 GB
2	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 74.9 t/s	74.9 tok/s	Q4_K_M · 19.3 GB
3	Qwen3 30B A3B Instruct 2507Alibaba Q4_K_M · 19.4 GB · 61.0 t/s	61.0 tok/s	Q4_K_M · 19.4 GB
4	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 58.8 t/s	58.8 tok/s	Q4_K_M · 13.1 GB
5	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 54.1 t/s	54.1 tok/s	Q4_K_M · 16.5 GB

#	Model	Speed	Agents Score	Quant · Memory
1	GPT OSS 120BOpenAIHow to run → Q4_K_M · 70.8 GB · 43.2 t/s	43.2 tok/s		Q4_K_M · 70.8 GB
2	Qwen3.8 27BAlibaba Q4_K_M · 17.9 GB · 10.2 t/s	10.2 tok/s		Q4_K_M · 17.9 GB
3	Qwen3.6 35B A3BAlibaba Q4_K_M · 22.0 GB · 49.2 t/s	49.2 tok/s	overall	Q4_K_M · 22.0 GB
4	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 74.9 t/s	74.9 tok/s		Q4_K_M · 19.3 GB
5	GLM 4.7 FlashZ.ai Q4_K_M · 19.9 GB · 47.2 t/s	47.2 tok/s		Q4_K_M · 19.9 GB

See all 399 models on the ASUS Ascent GX10 →Bars = traction for models without a Score yet

About the ASUS Ascent GX10

The ASUS Ascent GX10 is a 128 GB AI box with more memory than speed: it runs 14B and 120B MoE models well. The system keeps about 9 GB, leaving 119 GB for models. With 125 TFLOPS it reads long prompts faster than most 128 GB machines: a 4K-token prompt takes 1.0 s. At its $2,999 MSRP it gives 16.4 tok/s per $1,000, 4th of the 8 machines compared here. GB10 (Blackwell), released 2025.

Speed in 128 GB#6273 GB/s

Prompt reading#2125 TFLOPS

For models119 GBThe system keeps 9 GB

ChipGB10released 2025

ASUS Ascent GX10 strengths and weaknesses

Strengths

Runs 120B MoE models: GPT OSS 120B at 43.2 tok/s in 70.8 GB
Reads long prompts fast: A 32K-token prompt on Qwen3.6 35B A3B starts answering in 8.3 s
FP8 and NVFP4 run natively: Blackwell takes FP8 and NVFP4 checkpoints in vLLM as published

Weaknesses

Slow on large dense models: Llama 3.3 70B Instruct at 3.8 tok/s, Qwen3.8 27B at 10.2 tok/s

Memory for models

119 GB of 128 GB

35B MoE22 GB70B51.3 GB120B MoE70.8 GB228B116.7 GB

35B MoE22 GB120B MoE70.8 GB228B116.7 GB

For models 119 GBThe system keeps 9 GBModel size at Q4

Everything on the size ladder fits. Qwen3.6 35B A3B and Gemma 4 26B A4B IT together use 38.5 GB and leave 80.5 GB free.

Speed per dollar and per watt

NewUsed

On Qwen3.6 35B A3B (35B params, 3B active) at Q4_K_M. New means a shop price, either a street quote or the maker's own price; used is compared with used. The last two columns are the speed you get per $1,000 of price and per 100 W of power; higher is better. The ASUS Ascent GX10 has no current new price, so it is shown at its MSRP.

Machine	New price	tok/s	tok/s per $1,000	tok/s per 100 W
RTX 509032 GB	about $5,376	213	39.7	37.1
Framework Desktop Ryzen AI Max+ 395128 GB	about $1,999	46.7	23.4	33.4
Mac Studio M4 Max128 GB	about $3,499	64.2	18.3	44.3
ASUS Ascent GX10128 GB	about $2,999	49.2	16.4	–
Mac Studio M2 Ultra192 GB	about $5,599	75.9	13.6	25.7
MacBook Pro 16" M5 Max128 GB	about $5,399	67.8	12.6	–
DGX Spark128 GB	about $3,999	49.2	12.3	20.5
Mac Studio M3 Ultra256 GB	about $7,099	76.6	10.8	28.4

Machine	Used price	tok/s	tok/s per $1,000	tok/s per 100 W
RTX 409024 GB	about $3,000	151	50.3	33.6
RTX 509032 GB	about $6,400	213	33.3	37.1

Cost per token: the ASUS Ascent GX10 against 24–256 GB machines and GPUs

On Qwen3.6 35B A3B (35B params, 3B active, Q4_K_M, 4K context). Speed, cost per token and power per token depend on the model.

NewUsed

Speed$ per 1M tokens

24–36 GB96–128 GB192+ GBthis AI boxat MSRP

Cost per 1M output tokenson Qwen3.6 35B A3B · card over 3 years + power

$3.87

Machine, MSRP: $3.87
Power: not published

3-year cost of ownership$2,999

Or rent an A100 in the cloud$1.00/hr

Renting costs as much as buying after ≈3,000 hours (≈2.0 years at 4 h a day).

Power$/kWhUseh/dayKeepyears

Each dot is a machine or GPU; hover or tap it for its numbers, click to open it. Machines without a price for the chosen basis are left out. Machines without a published power figure are left out of Per watt and costed without power. How we calculate cost per token

Similar devices and alternatives

The same chip from other makers first, then machines and GPUs people weigh against it, each with the one reason it is worth a look. Speeds on Qwen3.6 35B A3B.

Same chip, 1 GB more memory for $1,000 moreDGX SparkNVIDIA · 120 GB for models · GB10

same speed▲ $1,000 more▲ 1 GB$3,999

Same family 31% faster, 5.5 GB more memoryMac Studio M4 Max (128 GB)Apple · 124.5 GB for models · M4 Max

▲ 31% speed▲ 5.5 GB$3,499

38% faster, 5.5 GB more memoryMacBook Pro 16" M5 Max (128 GB)Apple · 124.5 GB for models · M5 Max

▲ 38% speed▲ 5.5 GB$5,399

Machine, 5% slowerFramework Desktop Ryzen AI Max+ 395Framework · 96 GB for models · Ryzen AI Max+ 395

▼ 5% speed▼ 23 GB$1,999

3.1× faster if your models fit in 24 GBRTX 4090NVIDIA · 24 GB VRAM · GPU

▲ 207% speed▼ 95 GB$1,599rent $0.34/hr

4.3× faster if your models fit in 32 GBRTX 5090NVIDIA · 32 GB VRAM · GPU

▲ 334% speed▼ 87 GB$5,376rent $0.50/hr

ASUS Ascent GX10 tokens per second by model size

Output speed depends on memory bandwidth (273 GB/s). Grey rows need more than the 119 GB available.

9BQwen3.5 9B · Q4_K_M · 6.6 GB
27.9tok/s
14BQwen3 14B · Q4_K_M · 11.9 GB
18.7tok/s
27–31BQwen3.8 27B · Q4_K_M · 17.9 GB
10.2tok/s
35B MoEQwen3.6 35B A3B · Q4_K_M · 22.0 GB
49.2tok/s
70BLlama 3.3 70B Instruct · Q4_K_M · 51.3 GB slow
3.8tok/s
120B MoEGPT OSS 120B · Q4_K_M · 70.8 GB
43.2tok/s

Estimated speeds: Q4_K_M, 4K context, one user. How we estimate

Unified-memory platforms: writing vs compute

Writing, tok/sCompute, TFLOPS

Orin64 GB · 204.8 GB/s
41.7
43
Ryzen AI Max+ 395128 GB · 256 GB/s
46.7
30
GB10128 GB · 273 GB/s
49.2
125
Jetson T5000 (Thor)128 GB · 273 GB/s
54.0
259
M4 Pro64 GB · 273 GB/s
43.2
17

Machines with about the same memory bandwidth write at about the same speed; compute decides how fast prompts are read. Speeds on Qwen3.6 35B A3B.

All 1288 models on the ASUS Ascent GX10

Featured only

Best quant that fits in 119 GB, ordered by llmrun Score. Fit grades how well it runs here, S best. How ranking works

LLM models compatible with ASUS Ascent GX10 — ranked by Score, recency and Fit
Model	Quant	VRAM	Speed	Context	Fit
Molmo2 8B8.7BVision Q4_K_M·30.6 t/s	Q4_K_M	7.9 GB7%	30.6 t/s	37K	A71, Runs well
SenseNova Loop 9B Preview9.7BVisionChatFunctions Q4_K_M·27.9 t/s	Q4_K_M	8.2 GB7%	27.9 t/s	262K	A69, Runs well
Apertus V1.5 8B8.9BVision Q4_K_M·30.2 t/s	Q4_K_M	8.5 GB7%	30.2 t/s	—	A71, Runs well
Seed OSS 36B Instruct36.2BChatFunctions Q4_K_M·8.0 t/s	Q4_K_M	24.1 GB20%	8.0 t/s	524K	B45, Decent
Tiny Qwen3ForCausalLM Instruct 25071MChatFunctions Q4_K_M·591.5 t/s	Q4_K_M	0.5 GB0%	591.5 t/s	262K	S100, Runs great
Beetle Monolingual Humanscale Eng194MChat BF16·412.7 t/s	BF16	0.4 GB0%	412.7 t/s	1K	S100, Runs great
Ornith 1.0 9B9.4BChatFunctions Q4_K_M·28.6 t/s	Q4_K_M	6.5 GB5%	28.6 t/s	262K	A69, Runs well
Crowd V11.0BChatFunctions BF16·79.9 t/s	BF16	3.7 GB3%	79.9 t/s	—	S88, Runs great
Distil Lfm25 Shellper354MChatFunctions Q4_K_M·305.9 t/s	Q4_K_M	0.8 GB1%	305.9 t/s	128K	S100, Runs great
NVIDIA Nemotron 3.5 Bolt E4B 4GB4BChat Q4_K_M·67.2 t/s	Q4_K_M	4.8 GB4%	67.2 t/s	—	S85, Runs great
Gemma4 12B QAT Uncensored HauhauCS Balanced12BVisionRoleplayChat Q4_K_M·22.4 t/s	Q4_K_M	10.8 GB9%	22.4 t/s	—	B62, Decent
JevK54.2BChatFunctions Q4_K_M·59.3 t/s	Q4_K_M	3.2 GB3%	59.3 t/s	262K	A84, Runs well
LFM2.5 230M230MChatFunctions Q4_K_M·354.9 t/s	Q4_K_M	0.6 GB1%	354.9 t/s	128K	S100, Runs great
DeepSeek R1 0528 Qwen3 8B8.2BChatReasoningFunctions Q4_K_M·32.1 t/s	Q4_K_M	7.6 GB6%	32.1 t/s	131K	A71, Runs well
Qwen3 Next 80B A3B Thinking81.3BChatFunctions Q4_K_M·42.3 t/s	Q4_K_M	49.3 GB41%	42.3 t/s	262K	A76, Runs well

ASUS Ascent GX10 specs

Specs

Chip: GB10 · Blackwell GPU (GB10)
CPU cores: 20
GPU cores: 6,144
Unified memory: 128 GB LPDDR5X
For models: 119 GB (The system keeps 9 GB)
Memory bandwidth: 273 GB/s
FP16 (dense): 125 TFLOPS
Size: stackable chassis
Networking: ConnectX-7 200GbE
Released: 2025-10-15
MSRP: $2,999

ASUS Ascent GX10 FAQ

Is the ASUS Ascent GX10 worth it for local LLMs in 2026?

At its $2,999 MSRP it gives 16.4 tok/s per $1,000 on Qwen3.6 35B A3B, 4th of the 8 machines compared here. It runs 14B and 120B MoE models well; 27–31B and 70B fit but are slow (10 and 4 tok/s).

How much memory is available for AI on the ASUS Ascent GX10?

About 119 GB of the 128 GB. The system keeps roughly 9 GB for itself and other apps.

What is the largest model the ASUS Ascent GX10 can run?

MiniMax M2.7 (228.7B) is the largest at 4-bit or better: at Q4_0 it uses 116.7 GB, 98% of the available memory, and runs at about 26.7 tok/s.

Can the ASUS Ascent GX10 run Qwen3.6 35B A3B?

Yes. Qwen3.6 35B A3B fits at Q4_K_M, using 22.0 GB of the 119 GB available, and it is the best model that runs well on this machine.

Can the ASUS Ascent GX10 run 70B models?

Yes, but slowly: Llama 3.3 70B Instruct at Q4_K_M uses 51.3 GB and writes about 3.8 tok/s.

How long does the ASUS Ascent GX10 take to read a long prompt?

On Qwen3.6 35B A3B, about 1.0 s for a 4K-token prompt and 8.3 s for a 32K-token document before the first word appears.

Is renting a GPU cheaper than buying the ASUS Ascent GX10?

An A100 (80 GB) rents from $1.00/hr. Renting costs as much as buying after ≈3,000 hours (≈2.0 years at 4 h a day).

48 GB GPUs AI boxes Mac Pro M2 Ultra Mac Studio M1 Ultra Mac Studio M2 Ultra Mac Studio M5 Max MacBook Pro 14" M5 Max GMKtec EVO-X2 Ryzen AI Max+ 395 Best coding LLMs All hardware