MacBook Pro M4 32GBBudget pick
32 GB Unified (+16)
C
Adds memory headroom for longer context windows and future model growth.21 tok/s decode
Adds memory headroom for longer context windows and future model growth.
~$799 MSRP
DeepSeek R1 Distill Qwen 1.5B needs ~3.6 GB VRAM. RX 9070 16GB has 16.0 GB. With Q4_K_M quantization, expect ~21 tok/s.
Operating mode
Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.
Current mode
Balanced
Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.
Select quantization to explore
Fit status
Runs well
Decode
21.0 tok/s
TTFT
9219 ms
Safe context
1.1M
Memory
3.6 GB / 16.0 GB
This setup is broadly balanced for this model.
No major red flags
This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | C | Runs well | 21.0 tok/s | 5029 ms | 1.0M |
| Coding | C | Runs well | 21.0 tok/s | 9219 ms | 1.1M |
| Agentic Coding | C | Runs well | 21.0 tok/s | 13410 ms | 1.1M |
| Reasoning | C | Runs well | 21.0 tok/s | 10895 ms | 1.1M |
| RAG | C | Runs well | 21.0 tok/s | 16762 ms | 1.1M |
How DeepSeek R1 Distill Qwen 1.5B (1.5B params) fits at each quantization level on RX 9070 16GB (16.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 0.6 GB | Low | C45 |
Q3_K_S | 3 | 0.7 GB | Low | C45 |
NVFP4 | 4 | 0.8 GB | Medium | C46 |
Q4_K_M | 4 | 0.9 GB | Medium | C46 |
Q5_K_M | 5 | 1.1 GB | High | C46 |
Q6_K | 6 | 1.2 GB | High | C46 |
Q8_0 | 8 | 1.6 GB | Very High | C46 |
F16Best for your GPU | 16 | 3.1 GB | Maximum | C47 |
Copy-paste commands to run DeepSeek R1 Distill Qwen 1.5B on your machine.
Run
lms load hf-unsloth--deepseek-r1-distill-qwen-1-5b-gguf && lms server startUpgrade options
Adds memory headroom for longer context windows and future model growth.
~$799 MSRP
~$1,099 MSRP
Yes, RX 9070 16GB can run DeepSeek R1 Distill Qwen 1.5B with a C grade (Runs well). Expected decode speed: 21.0 tok/s.
DeepSeek R1 Distill Qwen 1.5B (1.5B parameters) requires approximately 3.6 GB of memory with Q4_K_M quantization.
The recommended quantization for DeepSeek R1 Distill Qwen 1.5B is Q4_K_M, which balances quality and memory efficiency.
On RX 9070 16GB, DeepSeek R1 Distill Qwen 1.5B achieves approximately 21.0 tokens per second decode speed with a time-to-first-token of 9219ms using Q4_K_M quantization.
For coding workloads, DeepSeek R1 Distill Qwen 1.5B on RX 9070 16GB receives a C grade with 21.0 tok/s and 1.1M context.
On RX 9070 16GB, DeepSeek R1 Distill Qwen 1.5B can safely use up to 1.1M tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/hf-unsloth--deepseek-r1-distill-qwen-1-5b-gguf-on-rx-9070-16gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: