Skywork Reward V2 Llama 3.1 8B on Intel Arc B580

Can the Intel Arc B580 run Skywork Reward V2 Llama 3.1 8B?

Yes, but slowly (tight fit)

Slow (tight fit). At Q8_0 it needs about 10.4 GB of 12.0 GB usable and makes one decision in about 560 ms.

Best precision: Q8_0
Time per decision: 560 ms
Decisions per second: 1.8/s
Input assumed: 1,024 tokens
Returns: Probability or score

Best app to run it on the Intel Arc B580

On Windows

vLLM

Inference server · runs on vLLM

Serves the scoring head directly (rerank, classify or reward) with batching.
On Windows it runs through WSL2.

vllm serve Skywork/Skywork-Reward-V2-Llama-3.1-8B

Sentence Transformers Can only use the CPU on this hardware, so it will be slow.

On Linux

vLLM

Inference server · runs on vLLM

Serves the scoring head directly (rerank, classify or reward) with batching.

vllm serve Skywork/Skywork-Reward-V2-Llama-3.1-8B

Sentence Transformers Can only use the CPU on this hardware, so it will be slow.

How we choose: the files published for this model, your operating system and GPU, whether it fits fully in memory, and published speed tests (MLX vs llama.cpp on Apple silicon, vLLM vs llama.cpp vs Ollama on NVIDIA). Details.

Download Skywork Reward V2 Llama 3.1 8B

Original weights · Hugging Face

Full-precision files from Skywork, for Transformers, Sentence Transformers, Text Embeddings Inference, Infinity or vLLM.

huggingface.co/Skywork/Skywork-Reward-V2-Llama-3.1-8B (opens in a new tab)

No sign-in needed.

Links checked 3 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 90Excellent quality (S) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q8_0, from its editorial quality tier scaled by the quantization or precision. It’s the same on any hardware that runs this variant. Scale: S 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Slowtight fit: How well it runs on the Intel Arc B580: speed, capped by how well it fits in memory. Runs great: 30+ tokens/s (or near the image, video or decision speed target) · Runs well: 10+ tokens/s · Slow: 3+ tokens/s · Very slow: under 3 · Won’t run: doesn’t fit even with offload. A tight fit or RAM offload caps it at Runs well; heavy offload caps it at Slow.

Match score

To order lists, each result also gets a match score out of 100 from four parts. It favors the most capable model that still runs well.

PrecisionEditorial precision tier from the model’s published benchmarks, scaled by the quantization or precision used.	40.5 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.	24.0 / 25
SpeedTime for one decision against a 100 ms target: reading the input plus any tokens the model writes.	6.3 / 15
ClarityHow easy the answer is to use in code: a probability or score earns the most, written feedback before a score the least.	15.0 / 15
Match score	85.8 / 100

The match score orders results; it is not shown as a grade. Quality and Runs are the two ratings in the tables.

Every quantization on the Intel Arc B580

Quant	Memory needed	Available	Time per decision	Runs	Quality	Download
`Q8_0`	10.4 GB	12.0 GB	560 ms	Slowtight fit	90Excellent quality (S) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`F16`	17.5 GB	12.0 GB	—	Won't run	90Excellent quality (S) · 90 of 100: how capable the model is at F16, whatever it runs on. Match score 12/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)

Times are for one request with a 1,024-token input. Batching servers process many requests at once.

Other hardware that runs it

90Excellent quality (S) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell Q8_0 · 97 ms · Runs great
90Excellent quality (S) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX Q8_0 · 114 ms · Runs great
90Excellent quality (S) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Q8_0 · 115 ms · Runs great
90Excellent quality (S) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT Q8_0 · 142 ms · Runs well
90Excellent quality (S) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 Q8_0 · 144 ms · Runs well
90Excellent quality (S) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5080 Q8_0 · 210 ms · Runs well

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.