AMD · Ryzen AI 7 350 · Laptop
Best AI Models for AMD Ryzen AI 7 350 (Krackan 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.
| # | Model | Speed | llmrun Score | Quant · Memory |
|---|---|---|---|---|
| 1 | Qwen3.6 35B A3BAlibabaHow to run → Q4_K_M · 22.0 GB · 20.7 t/s | 20.7 tok/s | Q4_K_M · 22.0 GB | |
| 2 | Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 22.6 t/s | 22.6 tok/s | Q4_K_M · 16.5 GB | |
| 3 | Qwen3 30B A3B Thinking 2507Alibaba Q4_K_M · 19.4 GB · 26.2 t/s | 26.2 tok/s | Q4_K_M · 19.4 GB | |
| 4 | GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 24.5 t/s | 24.5 tok/s | Q4_K_M · 13.1 GB | |
| 5 | Q4_K_M · 19.3 GB · 32.8 t/s | 32.8 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 · 20.7 t/s | 20.7 tok/s | Q4_K_M · 22.0 GB | |
| 2 | Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 22.6 t/s | 22.6 tok/s | Q4_K_M · 16.5 GB | |
| 3 | GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 24.5 t/s | 24.5 tok/s | Q4_K_M · 13.1 GB | |
| 4 | Qwen3 30B A3B Thinking 2507Alibaba Q4_K_M · 19.4 GB · 26.2 t/s | 26.2 tok/s | overall | Q4_K_M · 19.4 GB |
| 5 | Q4_K_M · 19.3 GB · 32.8 t/s | 32.8 tok/s | Q4_K_M · 19.3 GB |
| # | Model | Speed | Long context Score | Quant · Memory |
|---|---|---|---|---|
| 1 | Q4_K_M · 16.5 GB · 22.6 t/s | 22.6 tok/s | Q4_K_M · 16.5 GB | |
| 2 | Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 22.1 t/s | 22.1 tok/s | Q4_K_M · 3.4 GB | |
| 3 | GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 24.5 t/s | 24.5 tok/s | Q4_K_M · 13.1 GB | |
| 4 | Qwen3.6 35B A3BAlibaba Q4_K_M · 22.0 GB · 20.7 t/s | 20.7 tok/s | Q4_K_M · 22.0 GB | |
| 5 | LFM2.5 24B A2BLiquid AI Q4_K_M · 15.0 GB · 34.3 t/s | 34.3 tok/s | Q4_K_M · 15.0 GB |
| # | Model | Speed ↓ | llmrun Score | Quant · Memory |
|---|---|---|---|---|
| 1 | Q4_K_M · 19.4 GB · 26.2 t/s | 26.2 tok/s | Q4_K_M · 19.4 GB | |
| 2 | Q4_K_M · 19.3 GB · 32.8 t/s | 32.8 tok/s | Q4_K_M · 19.3 GB | |
| 3 | Qwen3 30B A3B Instruct 2507Alibaba Q4_K_M · 19.4 GB · 26.2 t/s | 26.2 tok/s | Q4_K_M · 19.4 GB | |
| 4 | GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 24.5 t/s | 24.5 tok/s | Q4_K_M · 13.1 GB | |
| 5 | Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 22.6 t/s | 22.6 tok/s | Q4_K_M · 16.5 GB |
| # | Model | Speed | Vision Score | Quant · Memory |
|---|---|---|---|---|
| 1 | Qwen3.6 35B A3BAlibabaHow to run → Q4_K_M · 22.0 GB · 20.7 t/s | 20.7 tok/s | Q4_K_M · 22.0 GB | |
| 2 | Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 22.6 t/s | 22.6 tok/s | Q4_K_M · 16.5 GB | |
| 3 | Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 22.1 t/s | 22.1 tok/s | Q4_K_M · 3.4 GB | |
| 4 | Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 25.4 t/s | 25.4 tok/s | Q4_K_M · 5.0 GB | |
| 5 | MiniCPM V 4.7 35B A3BOpenBMB Q4_K_M · 22.1 GB · 23.8 t/s | 23.8 tok/s | Q4_K_M · 22.1 GB |
The AMD Ryzen AI 7 350 (Krackan 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 29 s before the first word on Qwen3.6 35B A3B. Ryzen AI 7 350, released 2025.
AMD Ryzen AI 7 350 (Krackan 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 3.8 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 GB70B models need 51.3 GB at Q4, more than the 24 GB available.Or rent an H100 (80 GB) from $2.69/hr →
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.
Output speed depends on memory bandwidth (120 GB/s). Grey rows need more than the 24 GB available.
- 9BQwen3.5 9B · Q4_K_M · 6.6 GB11.3tok/s
- 7.6tok/s
- 4.1tok/s
- 35B MoEQwen3.6 35B A3B · Q4_K_M · 22.0 GB20.7tok/s
- 70BLlama 3.3 70B Instruct · not at 4-bitneeds 51.3 GB
- 120B MoEGPT OSS 120B · not at 4-bitneeds 70.8 GB
Estimated speeds: Q4_K_M, 4K context, one user. How we estimate
All 1158 models on the AMD Ryzen AI 7 350 (Krackan Point) Laptop
Featured onlyBest quant that fits in 24 GB, ordered by llmrun Score. Fit grades how well it runs here, S best. How ranking works
| Model | Quant | VRAM | Speed | Context | Score | Fit |
|---|---|---|---|---|---|---|
Seed OSS 36B InstructChatFunctions | Q4_K_S | 22.8 GB | 3.4 t/s | 524K | D17, Barely runs | |
Tmax 27BChatFunctions | Q4_K_M | 17.3 GB | 4.3 t/s | 262K | C41, Usable | |
GPT OSS BF16ChatFunctions | Q4_K_M | 0.3 GB | 240.0 t/s | 131K | S100, Runs great | |
Surya Ocr 2Vision | Q4_K_M | 0.8 GB | 94.7 t/s | 262K | S90, Runs great | |
| Q4_K_M | 0.3 GB | 240.0 t/s | 8K | S100, Runs great | ||
BitCPM CANN 8BChat | Q4_K_M | 5.6 GB | 13.9 t/s | 33K | B53, Decent | |
VibeThinker 3BChatMathCodeReasoning | Q4_K_M | 2.8 GB | 32.3 t/s | 131K | A72, Runs well | |
Tmax 9BChatFunctions | Q4_K_M | 6.2 GB | 12.1 t/s | 262K | B51, Decent | |
Cosmos Reason2 8BVisionChatReasoningFunctions | Q4_K_M | 8.4 GB | 12.4 t/s | — | B51, Decent | |
Olmo 3.1 32B InstructChatFunctions | Q4_K_M | 21.5 GB | 3.6 t/s | 66K | D26, Barely runs | |
| Q4_K_M | 2.7 GB | 26.7 t/s | 131K | A68, Runs well | ||
Qwen3.5 35B A3BVision | Q4_K_M | 22.0 GB | 20.7 t/s | 262K | C44, Usable | |
| Q4_K_M | 7.1 GB | 15.6 t/s | — | B55, Decent | ||
OvisOCR3VisionFunctions | Q4_K_M | 0.9 GB | 83.7 t/s | 262K | S88, Runs great | |
| Q4_K_M | 0.3 GB | 232.3 t/s | 8K | S100, Runs great |
Specs
- Chip
- Ryzen AI 7 350 · Radeon 860M
- CPU cores
- 8
- GPU cores
- 8
- Unified memory
- 32 GB LPDDR5X-7500 (rated up to LPDDR5X-8000 / DDR5-5600)
- For models
- 24 GB (The system keeps 8 GB)
- Memory bandwidth
- 120 GB/s
- FP16 (dense)
- 6.1 TFLOPS
- NPU
- XDNA 2 NPU (50 TOPS)
- Power
- 28 W max
- Released
- 2025-01-06
AMD Ryzen AI 7 350 (Krackan Point) Laptop FAQ
How much memory is available for AI on the AMD Ryzen AI 7 350 (Krackan 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 7 350 (Krackan 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 7 350 (Krackan 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 7 350 (Krackan Point) Laptop take to read a long prompt?
On Qwen3.6 35B A3B, about 29 s for a 4K-token prompt and 3.8 min for a 32K-token document before the first word appears.
Is renting a GPU cheaper than buying the AMD Ryzen AI 7 350 (Krackan Point) Laptop?
An RTX 5090 (32 GB) rents from $0.48/hr.