llmrun

AMD · Ryzen AI 9 HX 370 · Laptop

Best AI Models for AMD Ryzen AI 9 HX 370 (Strix Point) Laptop (32 GB)

Runs 35B MoE models well; 9B, 14B and 27–31B fit but are slow (11, 8 and 4 tok/s), and 70B doesn't fit in 24 GB.

32 GB unified24 GB for models120 GB/s12 TFLOPS FP1628 W2024

What LLMs can the AMD Ryzen AI 9 HX 370 (Strix Point) Laptop run?

#ModelSpeed ↓llmrun ScoreQuant · Memory
1
Qwen3 30B A3B Thinking 2507AlibabaHow to run →
Q4_K_M · 19.4 GB · 26.2 t/s
26.2 tok/sQ4_K_M · 19.4 GB
2
NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA
Q4_K_M · 19.3 GB · 32.8 t/s
32.8 tok/sQ4_K_M · 19.3 GB
3
Qwen3 30B A3B Instruct 2507Alibaba
Q4_K_M · 19.4 GB · 26.2 t/s
26.2 tok/sQ4_K_M · 19.4 GB
4
GPT OSS 20BOpenAI
Q4_K_M · 13.1 GB · 24.5 t/s
24.5 tok/sQ4_K_M · 13.1 GB
5
Gemma 4 26B A4B ITGoogle
Q4_K_M · 16.5 GB · 22.6 t/s
22.6 tok/sQ4_K_M · 16.5 GB
See all 327 models on the AMD Ryzen AI 9 HX 370 (Strix Point) Laptop →Bars = traction for models without a Score yet

About the AMD Ryzen AI 9 HX 370 (Strix Point) Laptop

The AMD Ryzen AI 9 HX 370 (Strix 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 15 s before the first word on Qwen3.6 35B A3B. Ryzen AI 9 HX 370, released 2024.

Speed in 32 GB#9120 GB/s
Prompt reading#712 TFLOPS
For models24 GBThe system keeps 8 GB
ChipRyzen AI 9 HX 370released 2024

AMD Ryzen AI 9 HX 370 (Strix Point) Laptop strengths and weaknesses

Strengths

  • Runs 35B MoE models: Qwen3.6 35B A3B at 20.7 tok/s in 22 GB
  • Low power draw: 28 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 4.1 tok/s
  • Slow prompt reading: A 32K-token prompt on Qwen3.6 35B A3B waits 2.0 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 A100 (80 GB) from $1.14/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.

124% faster, 3.5 GB less memoryMac Mini M4 Pro (24 GB)Apple · 20.5 GB for models · M4 Pro
▲ 124% speed▼ 3.5 GBabout $1,599
24% faster, 3.5 GB less memoryMacBook Air 13" M4 (24 GB)Apple · 20.5 GB for models · M4
▲ 24% speed▼ 3.5 GBabout $1,399
38% faster, 4.5 GB more memoryMacBook Pro 14 M5Apple · 28.5 GB for models · M5
▲ 38% speed▲ 4.5 GBabout $1,839
167% faster, 8.5 GB more memoryMac Studio M4 Max (36 GB)Apple · 32.5 GB for models · M4 Max
▲ 167% speed▲ 8.5 GBabout $2,499
Reads prompts 28× faster, 24 GB for modelsRTX 4090NVIDIA · 24 GB VRAM · GPU
▲ 28× prompts▲ 630% speedsame memoryabout $1,599rent $0.34/hr
Reads prompts 36× faster, 32 GB for modelsRTX 5090NVIDIA · 32 GB VRAM · GPU
▲ 36× prompts▲ 930% speed▲ 8 GBabout $5,376rent $0.50/hr

AMD Ryzen AI 9 HX 370 (Strix Point) Laptop tokens per second by model size

Output speed depends on memory bandwidth (120 GB/s). Grey rows need more than the 24 GB available.

  1. 9BQwen3.5 9B · Q4_K_M · 6.6 GB
    11.3tok/s
  2. 14BQwen3 14B · Q4_K_M · 11.9 GB slow
    7.6tok/s
  3. 27–31BQwen3.8 27B · Q4_K_M · 17.9 GB slow
    4.1tok/s
  4. 35B MoEQwen3.6 35B A3B · Q4_K_M · 22.0 GB
    20.7tok/s
  5. 70BLlama 3.3 70B Instruct · not at 4-bit
    needs 51.3 GB
  6. 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
  1. M116 GB · 68.3 GB/s
    24.9
    5
  2. M216 GB · 100 GB/s
    33.4
    7
  3. Orin NX16 GB · 102.4 GB/s
    37.0
    15
  4. M316 GB · 102.4 GB/s
    34.0
    7
  5. Ryzen AI 9 HX 37032 GB · 120 GB/s
    20.7
    12
  6. M416 GB · 120 GB/s
    38.1
    9

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 327 models on the AMD Ryzen AI 9 HX 370 (Strix 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 AI 9 HX 370 (Strix Point) Laptop — ranked by Score, recency and Fit
ModelVRAMScoreFit
Qwen3.8 27B
Q4_K_M·4.1 t/s
17.9 GBC40, Usable
Gemma 4 26B A4B IT
Q4_K_M·22.6 t/s
16.5 GBB63, Decent
NVIDIA Nemotron 3.5 Lightning 30B A3B BF16
Q4_K_M·32.8 t/s
19.3 GBA71, Runs well
Muse Glimmer 30B
Q4_K_M·3.9 t/s
19.6 GBC38, Usable
Qwen3.6 35B A3B
Q4_K_M·20.7 t/s
22.0 GBC44, Usable
GLM 4.7 Flash
Q4_K_M·20.0 t/s
19.9 GBB56, Decent
LFM2.5 24B A2B
Q4_K_M·34.3 t/s
15.0 GBA73, Runs well
Qwen3.5 4B
Q4_K_M·22.1 t/s
3.4 GBB62, Decent
Gemma 4 31B IT
Q4_K_M·3.5 t/s
21.7 GBD26, Barely runs
Qwen3.5 9B
Q4_K_M·11.3 t/s
6.6 GBB50, Decent
JEV 27B VL
Q4_K_M·4.1 t/s
17.9 GBC40, Usable
GPT OSS 20B
Q4_K_M·24.5 t/s
13.1 GBA65, Runs well
Gemma 4 12B IT
Q4_K_M·8.7 t/s
9.0 GBB46, Decent
Ornith 1.0 35B
Q4_K_M·24.3 t/s
21.5 GBB51, Decent
Ling 3.0 Tiny
Q4_K_M·56.2 t/s
5.5 GBA82, Runs well

AMD Ryzen AI 9 HX 370 (Strix Point) Laptop specs and power

Specs

Chip
Ryzen AI 9 HX 370 · Radeon 890M
CPU cores
12
GPU cores
16
Unified memory
32 GB LPDDR5X-7500 / DDR5-5600
For models
24 GB (The system keeps 8 GB)
Memory bandwidth
120 GB/s
FP16 (dense)
11.9 TFLOPS
NPU
XDNA 2 NPU (50 TOPS)
Power
28 W max
Released
2024-07-28

AMD Ryzen AI 9 HX 370 (Strix Point) Laptop FAQ

How much memory is available for AI on the AMD Ryzen AI 9 HX 370 (Strix 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 AI 9 HX 370 (Strix 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 20.7 tok/s.

Can the AMD Ryzen AI 9 HX 370 (Strix 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 AI 9 HX 370 (Strix Point) Laptop take to read a long prompt?

On Qwen3.6 35B A3B, about 15 s for a 4K-token prompt and 2.0 min for a 32K-token document before the first word appears.

Is renting a GPU cheaper than buying the AMD Ryzen AI 9 HX 370 (Strix Point) Laptop?

An RTX 5090 (32 GB) rents from $0.50/hr.

Related

24 GB GPUsLaptopsMac Studio M1 MaxMac Studio M2 MaxMacBook Pro 14" M1 MaxMacBook Pro 14" M2 MaxMacBook Pro 16" M1 MaxMacBook Pro 16" M2 MaxMacBook Pro 14" M3 ProMacBook Pro 16" M4 MaxBest coding LLMsAll hardware