RX 9060 XT 16GBBudget pick
16 GB VRAM (+8)320 GB/s (+64)
C
Raises estimated decode speed by about 83%.47.2 tok/s decode
Raises estimated decode speed by about 83%.
Adds memory headroom for longer context windows and future model growth.
~$349 MSRP
OpenChat 3.5 7B Starling v2.0 i1 needs ~6.8 GB VRAM. RX 590 8GB has 8.0 GB. With Q4_K_M quantization, expect ~26 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
Tight fit
Decode
25.8 tok/s
TTFT
7510 ms
Safe context
40K
Memory
6.8 GB / 8.0 GB
This setup is broadly balanced for this model.
Older PCIe generation
PCIe 3.0 is workable, but it compounds the penalty when you offload heavily or try to scale across multiple cards.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | C | Runs well | 25.8 tok/s | 4096 ms | 40K |
| Coding | C | Tight fit | 25.8 tok/s | 7510 ms | 40K |
| Agentic Coding | C | Runs with offload | 25.8 tok/s | 10923 ms | 40K |
| Reasoning | C | Tight fit | 25.8 tok/s | 8875 ms | 40K |
| RAG | C | Runs with offload | 25.8 tok/s | 13654 ms | 40K |
Inference speed
Estimated decode speed (tokens/sec) for OpenChat 3.5 7B Starling v2.0 i1 at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~98 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.
| GPU / Mac | Memory | Quant | Speed (tok/s) | Fits? |
|---|---|---|---|---|
 RTX 5090 32GB | 32 GB | Q4_K_M | 98.0 | Fits |
| RTX 4090 24GB | 24 GB | Q4_K_M | 98.0 | Fits |
| RTX 4080 Super 16GB | 16 GB | Q4_K_M | 98.0 | Fits |
| RTX 3090 24GB | 24 GB | Q4_K_M | 98.0 | Fits |
RX 7900 XTX 24GB | 24 GB | Q4_K_M | 98.0 | Fits |
Mac Studio M3 Ultra 256GB | 256 GB | Q4_K_M | 98.0 | Fits |
Mac Studio M2 Ultra 128GB | 128 GB | Q4_K_M | 98.0 | Fits |
Mac Studio M1 Ultra 128GB | 128 GB | Q4_K_M | 98.0 | Fits |
| RTX 4070 12GB | 12 GB | Q4_K_M | 88.5 | Fits |
MacBook Pro M4 Max 128GB | 128 GB | Q4_K_M | 87.8 | Fits |
MacBook Pro M4 Max 64GB | 64 GB | Q4_K_M | 87.8 | Fits |
MacBook Pro M3 Max 64GB | 64 GB | Q4_K_M | 56.2 | Fits |
| RTX 3060 12GB | 12 GB | Q4_K_M | 55.6 | Fits |
MacBook Pro M1 Max 64GB | 64 GB | Q4_K_M | 51.5 | Fits |
| RTX 4060 8GB | 8 GB | Q4_K_M | 46.5 | Tight |
MacBook Pro M4 Pro 48GB | 48 GB | Q4_K_M | 45.3 | Fits |
Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.
How OpenChat 3.5 7B Starling v2.0 i1 (7B params) fits at each quantization level on RX 590 8GB (8.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 2.7 GB | Low | C53 |
Q3_K_S | 3 | 3.4 GB | Low | C53 |
NVFP4 | 4 | 3.9 GB | Medium | C53 |
Q4_K_M | 4 | 4.3 GB | Medium | C53 |
Q5_K_MBest for your GPU | 5 | 5.0 GB | High | C52 |
Q6_K | 6 | 5.7 GB | High | F0 |
Q8_0 | 8 | 7.5 GB | Very High | F0 |
F16 | 16 | 14.3 GB | Maximum | F0 |
Copy-paste commands to run OpenChat 3.5 7B Starling v2.0 i1 on your machine.
Run
lms load hf-mradermacher--openchat-3-5-7b-starling-v2-0-i1-gguf && lms server startUpgrade options
Raises estimated decode speed by about 83%.
Adds memory headroom for longer context windows and future model growth.
~$349 MSRP
Raises estimated decode speed by about 135%.
Adds memory headroom for longer context windows and future model growth.
~$449 MSRP
Raises estimated decode speed by about 81%.
Adds memory headroom for longer context windows and future model growth.
~$479 MSRP
Yes, RX 590 8GB can run OpenChat 3.5 7B Starling v2.0 i1 with a C grade (Tight fit). Expected decode speed: 25.8 tok/s.
OpenChat 3.5 7B Starling v2.0 i1 (7B parameters) requires approximately 6.8 GB of memory with Q4_K_M quantization.
The recommended quantization for OpenChat 3.5 7B Starling v2.0 i1 is Q4_K_M, which balances quality and memory efficiency.
On RX 590 8GB, OpenChat 3.5 7B Starling v2.0 i1 achieves approximately 25.8 tokens per second decode speed with a time-to-first-token of 7510ms using Q4_K_M quantization.
For coding workloads, OpenChat 3.5 7B Starling v2.0 i1 on RX 590 8GB receives a C grade with 25.8 tok/s and 40K context.
On RX 590 8GB, OpenChat 3.5 7B Starling v2.0 i1 can safely use up to 40K 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-mradermacher--openchat-3-5-7b-starling-v2-0-i1-gguf-on-rx-590-8gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: