AMD · Ryzen 7 8845HS · Laptop

Best AI Models for AMD Ryzen 7 8845HS (Hawk Point) Laptop (32 GB)

Runs 35B MoE models well; 9B, 14B and 27–31B fit but are slow (9, 6 and 3 tok/s), and 70B doesn't fit in 24 GB.

32 GB unified24 GB for models89.6 GB/s8 TFLOPS FP1645 W2023

What LLMs can the AMD Ryzen 7 8845HS (Hawk Point) Laptop run?

#	Model	Speed	Quant · Memory
1	Qwen3.6 35B A3BAlibabaHow to run → Q4_K_M · 22.0 GB · 16.2 t/s	16.2 tok/s	Q4_K_M · 22.0 GB
2	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 17.5 t/s	17.5 tok/s	Q4_K_M · 16.5 GB
3	Qwen3 30B A3B Thinking 2507Alibaba Q4_K_M · 19.4 GB · 20.9 t/s	20.9 tok/s	Q4_K_M · 19.4 GB
4	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 18.9 t/s	18.9 tok/s	Q4_K_M · 13.1 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 26.8 t/s	26.8 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	Coding Score	Quant · Memory
1	Qwen3.6 35B A3BAlibabaHow to run → Q4_K_M · 22.0 GB · 16.2 t/s	16.2 tok/s		Q4_K_M · 22.0 GB
2	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 17.5 t/s	17.5 tok/s		Q4_K_M · 16.5 GB
3	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 18.9 t/s	18.9 tok/s		Q4_K_M · 13.1 GB
4	Qwen3 30B A3B Thinking 2507Alibaba Q4_K_M · 19.4 GB · 20.9 t/s	20.9 tok/s	overall	Q4_K_M · 19.4 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 26.8 t/s	26.8 tok/s		Q4_K_M · 19.3 GB

#	Model	Speed	Quant · Memory
1	Gemma 4 26B A4B ITGoogleHow to run → Q4_K_M · 16.5 GB · 17.5 t/s	17.5 tok/s	Q4_K_M · 16.5 GB
2	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 16.5 t/s	16.5 tok/s	Q4_K_M · 3.4 GB
3	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 18.9 t/s	18.9 tok/s	Q4_K_M · 13.1 GB
4	Qwen3.6 35B A3BAlibaba Q4_K_M · 22.0 GB · 16.2 t/s	16.2 tok/s	Q4_K_M · 22.0 GB
5	LFM2.5 24B A2BLiquid AI Q4_K_M · 15.0 GB · 27.6 t/s	27.6 tok/s	Q4_K_M · 15.0 GB

#	Model	Speed ↓	Quant · Memory
1	Qwen3 30B A3B Thinking 2507AlibabaHow to run → Q4_K_M · 19.4 GB · 20.9 t/s	20.9 tok/s	Q4_K_M · 19.4 GB
2	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 26.8 t/s	26.8 tok/s	Q4_K_M · 19.3 GB
3	Qwen3 30B A3B Instruct 2507Alibaba Q4_K_M · 19.4 GB · 20.9 t/s	20.9 tok/s	Q4_K_M · 19.4 GB
4	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 18.9 t/s	18.9 tok/s	Q4_K_M · 13.1 GB
5	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 17.5 t/s	17.5 tok/s	Q4_K_M · 16.5 GB

#	Model	Speed	Quant · Memory
1	Qwen3.6 35B A3BAlibabaHow to run → Q4_K_M · 22.0 GB · 16.2 t/s	16.2 tok/s	Q4_K_M · 22.0 GB
2	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 17.5 t/s	17.5 tok/s	Q4_K_M · 16.5 GB
3	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 16.5 t/s	16.5 tok/s	Q4_K_M · 3.4 GB
4	Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 18.9 t/s	18.9 tok/s	Q4_K_M · 5.0 GB
5	MiniCPM V 4.7 35B A3BOpenBMB Q4_K_M · 22.1 GB · 18.7 t/s	18.7 tok/s	Q4_K_M · 22.1 GB

See all 329 models on the AMD Ryzen 7 8845HS (Hawk Point) Laptop →Bars = traction for models without a Score yet

About the AMD Ryzen 7 8845HS (Hawk Point) Laptop

The AMD Ryzen 7 8845HS (Hawk Point) Laptop is a 32 GB laptop with more memory than speed: it runs 35B MoE models well. The system keeps about 8 GB, leaving 24 GB for models. Prompt reading is its weak spot: a 4K-token prompt waits 21 s before the first word on Qwen3.6 35B A3B. Ryzen 7 8845HS, released 2023.

Speed in 32 GB#1690 GB/s

Prompt reading#148 TFLOPS

For models24 GBThe system keeps 8 GB

ChipRyzen 7 8845HSreleased 2023

AMD Ryzen 7 8845HS (Hawk Point) Laptop strengths and weaknesses

Strengths

Runs 35B MoE models: Qwen3.6 35B A3B at 16.2 tok/s in 22 GB
Low power draw: 45 W at full load for the whole machine

Weaknesses

70B models don't fit: Llama 3.3 70B Instruct needs 51.3 GB at Q4 vs 24 GB usable here
Slow on large dense models: Qwen3.8 27B at 3.1 tok/s
Slow prompt reading: A 32K-token prompt on Qwen3.6 35B A3B waits 2.9 min for the first token
ROCm, not CUDA: No FP8 weights; MXFP4 only through llama.cpp, not vLLM

Memory for models

24 GB of 32 GB

9B6.6 GB14B11.9 GB27–31B17.9 GB35B MoE22 GB

9B6.6 GB14B11.9 GB35B MoE22 GB

For models 24 GBThe system keeps 8 GBModel size at Q4

70B models need 51.3 GB at Q4, more than the 24 GB available.Or rent an H100 (80 GB) from $2.69/hr →

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.

186% faster, 3.5 GB less memoryMac Mini M4 Pro (24 GB)Apple · 20.5 GB for models · M4 Pro

▲ 186% speed▼ 3.5 GB$1,599

59% faster, 3.5 GB less memoryMacBook Air 13" M4 (24 GB)Apple · 20.5 GB for models · M4

▲ 59% speed▼ 3.5 GB$1,399

91% faster, 4.5 GB more memoryMac Mini M6 (32 GB)Apple · 28.5 GB for models · M6

▲ 91% speed▲ 4.5 GB$1,299

77% faster, 4.5 GB more memoryMacBook Pro 14 M5Apple · 28.5 GB for models · M5

▲ 77% speed▲ 4.5 GB$1,839

Reads prompts 41× faster, 24 GB for modelsRTX 4090NVIDIA · 24 GB VRAM · GPU

▲ 41× prompts▲ 832% speedsame memory$1,599rent $0.34/hr

Reads prompts 52× faster, 32 GB for modelsRTX 5090NVIDIA · 32 GB VRAM · GPU

▲ 52× prompts▲ 1217% speed▲ 8 GB$5,502rent $0.50/hr

AMD Ryzen 7 8845HS (Hawk Point) Laptop tokens per second by model size

Output speed depends on memory bandwidth (90 GB/s). Grey rows need more than the 24 GB available.

9BQwen3.5 9B · Q4_K_M · 6.6 GB slow
8.5tok/s
14BQwen3 14B · Q4_K_M · 11.9 GB slow
5.7tok/s
27–31BQwen3.8 27B · Q4_K_M · 17.9 GB slow
3.1tok/s
35B MoEQwen3.6 35B A3B · Q4_K_M · 22.0 GB
16.2tok/s
70BLlama 3.3 70B Instruct · not at 4-bit
needs 51.3 GB
120B MoEGPT OSS 120B · not at 4-bit
needs 70.8 GB

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

Unified-memory platforms: writing vs compute

Writing, tok/sCompute, TFLOPS

M116 GB · 68.3 GB/s
24.9
5
Ryzen 7 8845HS32 GB · 89.6 GB/s
16.2
8
M216 GB · 100 GB/s
33.4
7
Orin NX16 GB · 102.4 GB/s
37.0
15
M316 GB · 102.4 GB/s
34.0
7
Core Ultra 9 285H32 GB · 119.5 GB/s
17.7
39

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 329 models on the AMD Ryzen 7 8845HS (Hawk Point) Laptop

Featured only

Best quant that fits in 24 GB, ordered by llmrun Score. Fit grades how well it runs here, S best. How ranking works

LLM models compatible with AMD Ryzen 7 8845HS (Hawk Point) Laptop — ranked by Score, recency and Fit
Model	Quant	VRAM	Speed	Context	Fit
Yi 9B8.8BChat Q4_K_M·9.3 t/s	Q4_K_M	6 GB25%	9.3 t/s	4K	B47, Decent
Qwen 14B14.2BChat Q4_K_M·5.7 t/s	Q4_K_M	10.6 GB44%	5.7 t/s	8K	C42, Usable
Baichuan2 7B Base7BChat Q4_K_M·11.6 t/s	Q4_K_M	5.0 GB21%	11.6 t/s	4K	B50, Decent
CodeQwen1.5 7B7.3BChatCode Q4_K_M·11.2 t/s	Q4_K_M	5.7 GB24%	11.2 t/s	66K	B49, Decent
Deepseek Coder 33B Instruct33.3BChatCode Q4_K_S·2.7 t/s	Q4_K_S	23.2 GB97%	2.7 t/s	16K	F12, Won't fit
Xgen 7B 8k Base7BChat Q4_K_M·11.6 t/s	Q4_K_M	5.7 GB24%	11.6 t/s	8K	B50, Decent
Yi 6B Chat6.1BChat Q4_K_M·13.2 t/s	Q4_K_M	4.2 GB18%	13.2 t/s	4K	B52, Decent
Baichuan 7B7BChat Q4_K_M·11.6 t/s	Q4_K_M	5.0 GB21%	11.6 t/s	4K	B50, Decent
Baichuan2 13B Base13BChat Q4_K_M·6.3 t/s	Q4_K_M	11.5 GB48%	6.3 t/s	—	C43, Usable
Internlm 7B7BChat FP16·3.5 t/s	FP16	15.4 GB64%	3.5 t/s	2K	C40, Usable
RedPajama INCITE 7B Base7BChat Q4_K_M·11.6 t/s	Q4_K_M	4.6 GB19%	11.6 t/s	2K	B50, Decent
Falcon 40B Instruct40BChat IQ3_M·2.7 t/s	IQ3_M	23.8 GB99%	2.7 t/s	—	F9, Won't fit
Baichuan 13B Base13BChat Q4_K_M·6.3 t/s	Q4_K_M	11.5 GB48%	6.3 t/s	—	C43, Usable
Qwen2.5 Coder 3B3.1BChatCodeFunctions Q4_K_M·24.1 t/s	Q4_K_M	2.8 GB12%	24.1 t/s	33K	B64, Decent
Qwen1.5 14B14.2BChat Q4_K_M·5.1 t/s	Q4_K_M	22.2 GB93%	5.1 t/s	33K	D22, Barely runs

AMD Ryzen 7 8845HS (Hawk Point) Laptop specs and power

Specs

Chip: Ryzen 7 8845HS · Radeon 780M
CPU cores: 8
GPU cores: 12
Unified memory: 32 GB DDR5-5600 SODIMM (dual-channel) or LPDDR5X-7500
For models: 24 GB (The system keeps 8 GB)
Memory bandwidth: 89.6 GB/s
FP16 (dense): 8.3 TFLOPS
NPU: Ryzen AI NPU (16 TOPS)
Power: 45 W max
Released: 2023-12-06

AMD Ryzen 7 8845HS (Hawk Point) Laptop FAQ

How much memory is available for AI on the AMD Ryzen 7 8845HS (Hawk Point) Laptop?

About 24 GB of the 32 GB. The system keeps roughly 8 GB for itself and other apps.

What is the largest model the AMD Ryzen 7 8845HS (Hawk Point) Laptop can run?

Qwen3.6 35B A3B (36.0B) is the largest at 4-bit or better: at Q4_K_M it uses 22.0 GB, 92% of the available memory, and runs at about 16.2 tok/s.

Can the AMD Ryzen 7 8845HS (Hawk Point) Laptop run 70B models?

No. Llama 3.3 70B Instruct needs 51.3 GB at Q4, more than the 24 GB available.

How long does the AMD Ryzen 7 8845HS (Hawk Point) Laptop take to read a long prompt?

On Qwen3.6 35B A3B, about 21 s for a 4K-token prompt and 2.9 min for a 32K-token document before the first word appears.

Is renting a GPU cheaper than buying the AMD Ryzen 7 8845HS (Hawk Point) Laptop?

An RTX 5090 (32 GB) rents from $0.48/hr.

24 GB GPUs Laptops Mac Studio M1 Max Mac Studio M2 Max MacBook Pro 14" M1 Max MacBook Pro 14" M2 Max MacBook Pro 16" M1 Max MacBook Pro 16" M2 Max AMD Ryzen AI 9 HX 370 (Strix Point) Laptop Best coding LLMs All hardware